[
  {
    "URL": "https://arxiv.org/abs/2008.05132v2",
    "archive": "arXiv",
    "archive_location": "2008.05132",
    "author": [
      {
        "literal": "Jieshan Chen"
      },
      {
        "literal": "Mulong Xie"
      },
      {
        "literal": "Zhenchang Xing"
      },
      {
        "literal": "Chunyang Chen"
      },
      {
        "literal": "Xiwei Xu"
      },
      {
        "literal": "Liming Zhu"
      },
      {
        "literal": "Guoqiang Li"
      }
    ],
    "citation-key": "arxiv_2008_05132",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "d6352985532945fd562ce0382aef0e977ce1ec5909b6872e5fe048167e9732a0",
        "submitted_at": "2020-08-12T06:36:33Z",
        "updated_at": "2020-09-07T12:57:33Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2008.05132v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2008.05132",
      "catalog_id": "arxiv:2008.05132",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2020-08-12",
      "identifiers": {
        "arxiv": "2008.05132"
      },
      "record_updated_at": "2020-09-07"
    },
    "genre": "preprint",
    "id": "arxiv:2008.05132",
    "issued": {
      "date-parts": [
        [
          2020,
          8,
          12
        ]
      ]
    },
    "note": "First published: 2020-08-12; Recorded arXiv version: v2; Recorded version updated: 2020-09-07T12:57:33Z.",
    "title": "Object Detection for Graphical User Interface: Old Fashioned or Deep Learning or a Combination?",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2010.04295v1",
    "archive": "arXiv",
    "archive_location": "2010.04295",
    "author": [
      {
        "literal": "Yang Li"
      },
      {
        "literal": "Gang Li"
      },
      {
        "literal": "Luheng He"
      },
      {
        "literal": "Jingjie Zheng"
      },
      {
        "literal": "Hong Li"
      },
      {
        "literal": "Zhiwei Guan"
      }
    ],
    "citation-key": "arxiv_2010_04295",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "68af0a0a4b605d0c968e8913232fde16e3eadf6361099e8fc3d015dcdb26302b",
        "submitted_at": "2020-10-08T22:56:03Z",
        "updated_at": "2020-10-08T22:56:03Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2010.04295v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2010.04295",
      "catalog_id": "arxiv:2010.04295",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "citation_edition": "record",
      "first_published_at": "2020-10-08",
      "identifiers": {
        "arxiv": "2010.04295"
      },
      "publication": {
        "authors": [
          "Yang Li",
          "Gang Li",
          "Luheng He",
          "Jingjie Zheng",
          "Hong Li",
          "Zhiwei Guan"
        ],
        "date_basis": "Explicit publisher metadata: 2020/11; precision=month.",
        "date_parts": [
          2020,
          11
        ],
        "doi": "10.18653/v1/2020.emnlp-main.443",
        "event_dates": null,
        "evidence_urls": [
          "https://aclanthology.org/2020.emnlp-main.443/"
        ],
        "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.",
        "issue": null,
        "notes": "The retained arXiv abstract reports 162,859 phrases; the ACL abstract reports 162,860. This publication proposal does not overwrite the arXiv annotation or assert a unified dataset count. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.",
        "pages": "5495-5510",
        "pdf_url": "https://aclanthology.org/2020.emnlp-main.443.pdf",
        "publisher": "Association for Computational Linguistics",
        "series": null,
        "title": "Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements",
        "type": "conference-paper",
        "url": "https://aclanthology.org/2020.emnlp-main.443/",
        "venue": "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
        "volume": null
      },
      "record_updated_at": "2020-10-08"
    },
    "genre": "preprint",
    "id": "arxiv:2010.04295",
    "issued": {
      "date-parts": [
        [
          2020,
          10,
          8
        ]
      ]
    },
    "note": "First published: 2020-10-08; Recorded arXiv version: v1; Recorded version updated: 2020-10-08T22:56:03Z.",
    "title": "Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2012.12350v2",
    "archive": "arXiv",
    "archive_location": "2012.12350",
    "author": [
      {
        "literal": "Zecheng He"
      },
      {
        "literal": "Srinivas Sunkara"
      },
      {
        "literal": "Xiaoxue Zang"
      },
      {
        "literal": "Ying Xu"
      },
      {
        "literal": "Lijuan Liu"
      },
      {
        "literal": "Nevan Wichers"
      },
      {
        "literal": "Gabriel Schubiner"
      },
      {
        "literal": "Ruby Lee"
      },
      {
        "literal": "Jindong Chen"
      },
      {
        "literal": "Blaise Agüera y Arcas"
      }
    ],
    "citation-key": "arxiv_2012_12350",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "51fdddb9a3d8a6090875719a51b22008b1f43bc38c6cfe1713a49a52f7e8434c",
        "submitted_at": "2020-12-22T20:49:52Z",
        "updated_at": "2021-01-25T20:37:39Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2012.12350v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2012.12350",
      "catalog_id": "arxiv:2012.12350",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2020-12-22",
      "identifiers": {
        "arxiv": "2012.12350"
      },
      "record_updated_at": "2021-01-25"
    },
    "genre": "preprint",
    "id": "arxiv:2012.12350",
    "issued": {
      "date-parts": [
        [
          2020,
          12,
          22
        ]
      ]
    },
    "note": "First published: 2020-12-22; Recorded arXiv version: v2; Recorded version updated: 2021-01-25T20:37:39Z.",
    "title": "ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2101.04893v1",
    "archive": "arXiv",
    "archive_location": "2101.04893",
    "author": [
      {
        "literal": "Xiaoyi Zhang"
      },
      {
        "literal": "Lilian de Greef"
      },
      {
        "literal": "Amanda Swearngin"
      },
      {
        "literal": "Samuel White"
      },
      {
        "literal": "Kyle Murray"
      },
      {
        "literal": "Lisa Yu"
      },
      {
        "literal": "Qi Shan"
      },
      {
        "literal": "Jeffrey Nichols"
      },
      {
        "literal": "Jason Wu"
      },
      {
        "literal": "Chris Fleizach"
      },
      {
        "literal": "Aaron Everitt"
      },
      {
        "literal": "Jeffrey P. Bigham"
      }
    ],
    "citation-key": "arxiv_2101_04893",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "d6a5305254ea405b6297c0a3eee43d58fc028abaa1a538d03b175b39b9daccca",
        "submitted_at": "2021-01-13T05:56:15Z",
        "updated_at": "2021-01-13T05:56:15Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2101.04893v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2101.04893",
      "catalog_id": "arxiv:2101.04893",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "adjacent",
      "first_published_at": "2021-01-13",
      "identifiers": {
        "arxiv": "2101.04893"
      },
      "record_updated_at": "2021-01-13"
    },
    "genre": "preprint",
    "id": "arxiv:2101.04893",
    "issued": {
      "date-parts": [
        [
          2021,
          1,
          13
        ]
      ]
    },
    "note": "First published: 2021-01-13; Recorded arXiv version: v1; Recorded version updated: 2021-01-13T05:56:15Z.",
    "title": "Screen Recognition: Creating Accessibility Metadata for Mobile Applications from Pixels",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2101.09465v2",
    "archive": "arXiv",
    "archive_location": "2101.09465",
    "author": [
      {
        "literal": "Xingyu Chen"
      },
      {
        "literal": "Zihan Zhao"
      },
      {
        "literal": "Lu Chen"
      },
      {
        "literal": "Danyang Zhang"
      },
      {
        "literal": "Jiabao Ji"
      },
      {
        "literal": "Ao Luo"
      },
      {
        "literal": "Yuxuan Xiong"
      },
      {
        "literal": "Kai Yu"
      }
    ],
    "citation-key": "arxiv_2101_09465",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "5fdf4bc31edd633fd0858835db0afedeef5dbc2694c4511903976c338bd19b1b",
        "submitted_at": "2021-01-23T09:43:44Z",
        "updated_at": "2021-11-08T08:31:44Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2101.09465v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2101.09465",
      "catalog_id": "arxiv:2101.09465",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2021-01-23",
      "identifiers": {
        "arxiv": "2101.09465"
      },
      "record_updated_at": "2021-11-08"
    },
    "genre": "preprint",
    "id": "arxiv:2101.09465",
    "issued": {
      "date-parts": [
        [
          2021,
          1,
          23
        ]
      ]
    },
    "note": "First published: 2021-01-23; Recorded arXiv version: v2; Recorded version updated: 2021-11-08T08:31:44Z.",
    "title": "WebSRC: A Dataset for Web-Based Structural Reading Comprehension",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2105.11941v2",
    "archive": "arXiv",
    "archive_location": "2105.11941",
    "author": [
      {
        "literal": "Jingwen Fu"
      },
      {
        "literal": "Xiaoyi Zhang"
      },
      {
        "literal": "Yuwang Wang"
      },
      {
        "literal": "Wenjun Zeng"
      },
      {
        "literal": "Sam Yang"
      },
      {
        "literal": "Grayson Hilliard"
      }
    ],
    "citation-key": "arxiv_2105_11941",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "8788e419d1a901f8ad9dd6089a12fe129baee764b1c285bbeb4ea60d7046afa2",
        "submitted_at": "2021-05-25T13:45:54Z",
        "updated_at": "2022-04-14T11:00:58Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2105.11941v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2105.11941",
      "catalog_id": "arxiv:2105.11941",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2021-05-25",
      "identifiers": {
        "arxiv": "2105.11941"
      },
      "record_updated_at": "2022-04-14"
    },
    "genre": "preprint",
    "id": "arxiv:2105.11941",
    "issued": {
      "date-parts": [
        [
          2021,
          5,
          25
        ]
      ]
    },
    "note": "First published: 2021-05-25; Recorded arXiv version: v2; Recorded version updated: 2022-04-14T11:00:58Z.",
    "title": "Understanding Mobile GUI: from Pixel-Words to Screen-Sentences",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2107.13731v2",
    "archive": "arXiv",
    "archive_location": "2107.13731",
    "author": [
      {
        "literal": "Chongyang Bai"
      },
      {
        "literal": "Xiaoxue Zang"
      },
      {
        "literal": "Ying Xu"
      },
      {
        "literal": "Srinivas Sunkara"
      },
      {
        "literal": "Abhinav Rastogi"
      },
      {
        "literal": "Jindong Chen"
      },
      {
        "literal": "Blaise Aguera y Arcas"
      }
    ],
    "citation-key": "arxiv_2107_13731",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "8a4f582015ccaf5bbe9be4b7ab925b2bbf6bd8451a4e63d89e1fe38363e26b31",
        "submitted_at": "2021-07-29T03:51:36Z",
        "updated_at": "2021-08-10T08:55:21Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2107.13731v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2107.13731",
      "catalog_id": "arxiv:2107.13731",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2021-07-29",
      "identifiers": {
        "arxiv": "2107.13731"
      },
      "record_updated_at": "2021-08-10"
    },
    "genre": "preprint",
    "id": "arxiv:2107.13731",
    "issued": {
      "date-parts": [
        [
          2021,
          7,
          29
        ]
      ]
    },
    "note": "First published: 2021-07-29; Recorded arXiv version: v2; Recorded version updated: 2021-08-10T08:55:21Z.",
    "title": "UIBert: Learning Generic Multimodal Representations for UI Understanding",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2108.03353v1",
    "archive": "arXiv",
    "archive_location": "2108.03353",
    "author": [
      {
        "literal": "Bryan Wang"
      },
      {
        "literal": "Gang Li"
      },
      {
        "literal": "Xin Zhou"
      },
      {
        "literal": "Zhourong Chen"
      },
      {
        "literal": "Tovi Grossman"
      },
      {
        "literal": "Yang Li"
      }
    ],
    "citation-key": "arxiv_2108_03353",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "9cf8d8521e643e1a888e706dff4e5106f178061d9af4ed2c2ba5ae42f194785a",
        "submitted_at": "2021-08-07T03:01:23Z",
        "updated_at": "2021-08-07T03:01:23Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2108.03353v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2108.03353",
      "catalog_id": "arxiv:2108.03353",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2021-08-07",
      "identifiers": {
        "arxiv": "2108.03353"
      },
      "record_updated_at": "2021-08-07"
    },
    "genre": "preprint",
    "id": "arxiv:2108.03353",
    "issued": {
      "date-parts": [
        [
          2021,
          8,
          7
        ]
      ]
    },
    "note": "First published: 2021-08-07; Recorded arXiv version: v1; Recorded version updated: 2021-08-07T03:01:23Z.",
    "title": "Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2112.05692v1",
    "archive": "arXiv",
    "archive_location": "2112.05692",
    "author": [
      {
        "literal": "Yang Li"
      },
      {
        "literal": "Gang Li"
      },
      {
        "literal": "Xin Zhou"
      },
      {
        "literal": "Mostafa Dehghani"
      },
      {
        "literal": "Alexey Gritsenko"
      }
    ],
    "citation-key": "arxiv_2112_05692",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "6e88e6e2659df232174d9fc71a2fac61a021941f096355f8ea3cd4c618c223d3",
        "submitted_at": "2021-12-10T17:37:26Z",
        "updated_at": "2021-12-10T17:37:26Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2112.05692v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2112.05692",
      "catalog_id": "arxiv:2112.05692",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2021-12-10",
      "identifiers": {
        "arxiv": "2112.05692"
      },
      "record_updated_at": "2021-12-10"
    },
    "genre": "preprint",
    "id": "arxiv:2112.05692",
    "issued": {
      "date-parts": [
        [
          2021,
          12,
          10
        ]
      ]
    },
    "note": "First published: 2021-12-10; Recorded arXiv version: v1; Recorded version updated: 2021-12-10T17:37:26Z.",
    "title": "VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modeling",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2201.04100v2",
    "archive": "arXiv",
    "archive_location": "2201.04100",
    "author": [
      {
        "literal": "Gang Li"
      },
      {
        "literal": "Gilles Baechler"
      },
      {
        "literal": "Manuel Tragut"
      },
      {
        "literal": "Yang Li"
      }
    ],
    "citation-key": "arxiv_2201_04100",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "d971ee06cafd46fe27a01d40bc16e3604e1d153c38ee92be970328d9935b0708",
        "submitted_at": "2022-01-11T17:52:40Z",
        "updated_at": "2022-01-13T17:53:31Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2201.04100v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2201.04100",
      "catalog_id": "arxiv:2201.04100",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2022-01-11",
      "identifiers": {
        "arxiv": "2201.04100"
      },
      "record_updated_at": "2022-01-13"
    },
    "genre": "preprint",
    "id": "arxiv:2201.04100",
    "issued": {
      "date-parts": [
        [
          2022,
          1,
          11
        ]
      ]
    },
    "note": "First published: 2022-01-11; Recorded arXiv version: v2; Recorded version updated: 2022-01-13T17:53:31Z.",
    "title": "Learning to Denoise Raw Mobile UI Layouts for Improving Datasets at Scale",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2209.08199v4",
    "archive": "arXiv",
    "archive_location": "2209.08199",
    "author": [
      {
        "literal": "Yu-Chung Hsiao"
      },
      {
        "literal": "Fedir Zubach"
      },
      {
        "literal": "Gilles Baechler"
      },
      {
        "literal": "Srinivas Sunkara"
      },
      {
        "literal": "Victor Carbune"
      },
      {
        "literal": "Jason Lin"
      },
      {
        "literal": "Maria Wang"
      },
      {
        "literal": "Yun Zhu"
      },
      {
        "literal": "Jindong Chen"
      }
    ],
    "citation-key": "arxiv_2209_08199",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "37f7ba5d5b9bbc96fd3a723e49190f296e08d2874dcd545272d3fcef3cc33d24",
        "submitted_at": "2022-09-16T23:49:00Z",
        "updated_at": "2025-02-09T21:09:17Z",
        "version": 4,
        "versioned_url": "https://arxiv.org/abs/2209.08199v4"
      },
      "canonical_source_url": "https://arxiv.org/abs/2209.08199",
      "catalog_id": "arxiv:2209.08199",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2022-09-16",
      "identifiers": {
        "arxiv": "2209.08199"
      },
      "record_updated_at": "2025-02-09"
    },
    "genre": "preprint",
    "id": "arxiv:2209.08199",
    "issued": {
      "date-parts": [
        [
          2022,
          9,
          16
        ]
      ]
    },
    "note": "First published: 2022-09-16; Recorded arXiv version: v4; Recorded version updated: 2025-02-09T21:09:17Z.",
    "title": "ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots",
    "type": "article",
    "version": "4"
  },
  {
    "URL": "https://arxiv.org/abs/2209.08655v2",
    "archive": "arXiv",
    "archive_location": "2209.08655",
    "author": [
      {
        "literal": "Bryan Wang"
      },
      {
        "literal": "Gang Li"
      },
      {
        "literal": "Yang Li"
      }
    ],
    "citation-key": "arxiv_2209_08655",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "65813c1784ba00e354aff4e38796b1bdc8e9b691cba9dd56b8232b5d86555d1b",
        "submitted_at": "2022-09-18T20:58:39Z",
        "updated_at": "2023-02-17T21:24:09Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2209.08655v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2209.08655",
      "catalog_id": "arxiv:2209.08655",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2022-09-18",
      "identifiers": {
        "arxiv": "2209.08655"
      },
      "record_updated_at": "2023-02-17"
    },
    "genre": "preprint",
    "id": "arxiv:2209.08655",
    "issued": {
      "date-parts": [
        [
          2022,
          9,
          18
        ]
      ]
    },
    "note": "First published: 2022-09-18; Recorded arXiv version: v2; Recorded version updated: 2023-02-17T21:24:09Z.",
    "title": "Enabling Conversational Interaction with Mobile UI using Large Language Models",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2209.14927v4",
    "archive": "arXiv",
    "archive_location": "2209.14927",
    "author": [
      {
        "literal": "Gang Li"
      },
      {
        "literal": "Yang Li"
      }
    ],
    "citation-key": "arxiv_2209_14927",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "eaa351e34fa6bdcbe26aa6714eacda1f667411090abfdd5575735605dc89e864",
        "submitted_at": "2022-09-29T16:45:43Z",
        "updated_at": "2023-02-24T01:41:32Z",
        "version": 4,
        "versioned_url": "https://arxiv.org/abs/2209.14927v4"
      },
      "canonical_source_url": "https://arxiv.org/abs/2209.14927",
      "catalog_id": "arxiv:2209.14927",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2022-09-29",
      "identifiers": {
        "arxiv": "2209.14927"
      },
      "record_updated_at": "2023-02-24"
    },
    "genre": "preprint",
    "id": "arxiv:2209.14927",
    "issued": {
      "date-parts": [
        [
          2022,
          9,
          29
        ]
      ]
    },
    "note": "First published: 2022-09-29; Recorded arXiv version: v4; Recorded version updated: 2023-02-24T01:41:32Z.",
    "title": "Spotlight: Mobile UI Understanding using Vision-Language Models with a Focus",
    "type": "article",
    "version": "4"
  },
  {
    "URL": "https://arxiv.org/abs/2210.02663v1",
    "archive": "arXiv",
    "archive_location": "2210.02663",
    "author": [
      {
        "literal": "Srinivas Sunkara"
      },
      {
        "literal": "Maria Wang"
      },
      {
        "literal": "Lijuan Liu"
      },
      {
        "literal": "Gilles Baechler"
      },
      {
        "literal": "Yu-Chung Hsiao"
      },
      {
        "literal": "Jindong"
      },
      {
        "literal": "Chen"
      },
      {
        "literal": "Abhanshu Sharma"
      },
      {
        "literal": "James Stout"
      }
    ],
    "citation-key": "arxiv_2210_02663",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "24d037f1abeb7708852ac5517ce02cc46622e359d9feab407f188c0657cc72f4",
        "submitted_at": "2022-10-06T03:48:54Z",
        "updated_at": "2022-10-06T03:48:54Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2210.02663v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2210.02663",
      "catalog_id": "arxiv:2210.02663",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2022-10-06",
      "identifiers": {
        "arxiv": "2210.02663"
      },
      "record_updated_at": "2022-10-06"
    },
    "genre": "preprint",
    "id": "arxiv:2210.02663",
    "issued": {
      "date-parts": [
        [
          2022,
          10,
          6
        ]
      ]
    },
    "note": "First published: 2022-10-06; Recorded arXiv version: v1; Recorded version updated: 2022-10-06T03:48:54Z.",
    "title": "Towards Better Semantic Understanding of Mobile Interfaces",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2210.03347v2",
    "archive": "arXiv",
    "archive_location": "2210.03347",
    "author": [
      {
        "literal": "Kenton Lee"
      },
      {
        "literal": "Mandar Joshi"
      },
      {
        "literal": "Iulia Turc"
      },
      {
        "literal": "Hexiang Hu"
      },
      {
        "literal": "Fangyu Liu"
      },
      {
        "literal": "Julian Eisenschlos"
      },
      {
        "literal": "Urvashi Khandelwal"
      },
      {
        "literal": "Peter Shaw"
      },
      {
        "literal": "Ming-Wei Chang"
      },
      {
        "literal": "Kristina Toutanova"
      }
    ],
    "citation-key": "arxiv_2210_03347",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "7ebb243c4690aba5f1a92b0d1e050399560998a7f304ea483dae2f451cf51ec0",
        "submitted_at": "2022-10-07T06:42:06Z",
        "updated_at": "2023-06-15T21:34:23Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2210.03347v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2210.03347",
      "catalog_id": "arxiv:2210.03347",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "adjacent",
      "first_published_at": "2022-10-07",
      "identifiers": {
        "arxiv": "2210.03347"
      },
      "record_updated_at": "2023-06-15"
    },
    "genre": "preprint",
    "id": "arxiv:2210.03347",
    "issued": {
      "date-parts": [
        [
          2022,
          10,
          7
        ]
      ]
    },
    "note": "First published: 2022-10-07; Recorded arXiv version: v2; Recorded version updated: 2023-06-15T21:34:23Z.",
    "title": "Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2210.03945v2",
    "archive": "arXiv",
    "archive_location": "2210.03945",
    "author": [
      {
        "literal": "Izzeddin Gur"
      },
      {
        "literal": "Ofir Nachum"
      },
      {
        "literal": "Yingjie Miao"
      },
      {
        "literal": "Mustafa Safdari"
      },
      {
        "literal": "Austin Huang"
      },
      {
        "literal": "Aakanksha Chowdhery"
      },
      {
        "literal": "Sharan Narang"
      },
      {
        "literal": "Noah Fiedel"
      },
      {
        "literal": "Aleksandra Faust"
      }
    ],
    "citation-key": "arxiv_2210_03945",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "9b9089164b5c784735d8915596fe902840e01c8215f507caed0e10d4361d13ec",
        "submitted_at": "2022-10-08T07:27:17Z",
        "updated_at": "2023-05-19T17:42:56Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2210.03945v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2210.03945",
      "catalog_id": "arxiv:2210.03945",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2022-10-08",
      "identifiers": {
        "arxiv": "2210.03945"
      },
      "record_updated_at": "2023-05-19"
    },
    "genre": "preprint",
    "id": "arxiv:2210.03945",
    "issued": {
      "date-parts": [
        [
          2022,
          10,
          8
        ]
      ]
    },
    "note": "First published: 2022-10-08; Recorded arXiv version: v2; Recorded version updated: 2023-05-19T17:42:56Z.",
    "title": "Understanding HTML with Large Language Models",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2301.10165v1",
    "archive": "arXiv",
    "archive_location": "2301.10165",
    "author": [
      {
        "literal": "Pratyay Banerjee"
      },
      {
        "literal": "Shweti Mahajan"
      },
      {
        "literal": "Kushal Arora"
      },
      {
        "literal": "Chitta Baral"
      },
      {
        "literal": "Oriana Riva"
      }
    ],
    "citation-key": "arxiv_2301_10165",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "bb647a96c7f8263786e85a5061c8c5284cb92ed0b2ebc4c405e1243b2ca3fa2b",
        "submitted_at": "2023-01-23T09:05:49Z",
        "updated_at": "2023-01-23T09:05:49Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2301.10165v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2301.10165",
      "catalog_id": "arxiv:2301.10165",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2023-01-23",
      "identifiers": {
        "arxiv": "2301.10165"
      },
      "record_updated_at": "2023-01-23"
    },
    "genre": "preprint",
    "id": "arxiv:2301.10165",
    "issued": {
      "date-parts": [
        [
          2023,
          1,
          23
        ]
      ]
    },
    "note": "First published: 2023-01-23; Recorded arXiv version: v1; Recorded version updated: 2023-01-23T09:05:49Z.",
    "title": "Lexi: Self-Supervised Learning of the UI Language",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2301.13280v1",
    "archive": "arXiv",
    "archive_location": "2301.13280",
    "author": [
      {
        "literal": "Jason Wu"
      },
      {
        "literal": "Siyan Wang"
      },
      {
        "literal": "Siman Shen"
      },
      {
        "literal": "Yi-Hao Peng"
      },
      {
        "literal": "Jeffrey Nichols"
      },
      {
        "literal": "Jeffrey P. Bigham"
      }
    ],
    "citation-key": "arxiv_2301_13280",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "0cc3b91aa85bc8c7d88a878c7b24926943eea0bcc92e25f517915242f2a82a39",
        "submitted_at": "2023-01-30T20:47:12Z",
        "updated_at": "2023-01-30T20:47:12Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2301.13280v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2301.13280",
      "catalog_id": "arxiv:2301.13280",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2023-01-30",
      "identifiers": {
        "arxiv": "2301.13280"
      },
      "record_updated_at": "2023-01-30"
    },
    "genre": "preprint",
    "id": "arxiv:2301.13280",
    "issued": {
      "date-parts": [
        [
          2023,
          1,
          30
        ]
      ]
    },
    "note": "First published: 2023-01-30; Recorded arXiv version: v1; Recorded version updated: 2023-01-30T20:47:12Z.",
    "title": "WebUI: A Dataset for Enhancing Visual UI Understanding with Web Semantics",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2310.04869v1",
    "archive": "arXiv",
    "archive_location": "2310.04869",
    "author": [
      {
        "literal": "Yue Jiang"
      },
      {
        "literal": "Eldon Schoop"
      },
      {
        "literal": "Amanda Swearngin"
      },
      {
        "literal": "Jeffrey Nichols"
      }
    ],
    "citation-key": "arxiv_2310_04869",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "a49e879891017071fce4df0ff4b07bd9e8b5a6e14385af565549aadbde1bc1cf",
        "submitted_at": "2023-10-07T16:32:34Z",
        "updated_at": "2023-10-07T16:32:34Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2310.04869v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2310.04869",
      "catalog_id": "arxiv:2310.04869",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2023-10-07",
      "identifiers": {
        "arxiv": "2310.04869"
      },
      "record_updated_at": "2023-10-07"
    },
    "genre": "preprint",
    "id": "arxiv:2310.04869",
    "issued": {
      "date-parts": [
        [
          2023,
          10,
          7
        ]
      ]
    },
    "note": "First published: 2023-10-07; Recorded arXiv version: v1; Recorded version updated: 2023-10-07T16:32:34Z.",
    "title": "ILuvUI: Instruction-tuned LangUage-Vision modeling of UIs from Machine Conversations",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2310.05126v1",
    "archive": "arXiv",
    "archive_location": "2310.05126",
    "author": [
      {
        "literal": "Jiabo Ye"
      },
      {
        "literal": "Anwen Hu"
      },
      {
        "literal": "Haiyang Xu"
      },
      {
        "literal": "Qinghao Ye"
      },
      {
        "literal": "Ming Yan"
      },
      {
        "literal": "Guohai Xu"
      },
      {
        "literal": "Chenliang Li"
      },
      {
        "literal": "Junfeng Tian"
      },
      {
        "literal": "Qi Qian"
      },
      {
        "literal": "Ji Zhang"
      },
      {
        "literal": "Qin Jin"
      },
      {
        "literal": "Liang He"
      },
      {
        "literal": "Xin Alex Lin"
      },
      {
        "literal": "Fei Huang"
      }
    ],
    "citation-key": "arxiv_2310_05126",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "39d5cf803efe3abaf70a9b78483bb0e750a8741adec1c4b7f3c05b9754d88560",
        "submitted_at": "2023-10-08T11:33:09Z",
        "updated_at": "2023-10-08T11:33:09Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2310.05126v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2310.05126",
      "catalog_id": "arxiv:2310.05126",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "adjacent",
      "first_published_at": "2023-10-08",
      "identifiers": {
        "arxiv": "2310.05126"
      },
      "record_updated_at": "2023-10-08"
    },
    "genre": "preprint",
    "id": "arxiv:2310.05126",
    "issued": {
      "date-parts": [
        [
          2023,
          10,
          8
        ]
      ]
    },
    "note": "First published: 2023-10-08; Recorded arXiv version: v1; Recorded version updated: 2023-10-08T11:33:09Z.",
    "title": "UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2312.08914v3",
    "archive": "arXiv",
    "archive_location": "2312.08914",
    "author": [
      {
        "literal": "Wenyi Hong"
      },
      {
        "literal": "Weihan Wang"
      },
      {
        "literal": "Qingsong Lv"
      },
      {
        "literal": "Jiazheng Xu"
      },
      {
        "literal": "Wenmeng Yu"
      },
      {
        "literal": "Junhui Ji"
      },
      {
        "literal": "Yan Wang"
      },
      {
        "literal": "Zihan Wang"
      },
      {
        "literal": "Yuxuan Zhang"
      },
      {
        "literal": "Juanzi Li"
      },
      {
        "literal": "Bin Xu"
      },
      {
        "literal": "Yuxiao Dong"
      },
      {
        "literal": "Ming Ding"
      },
      {
        "literal": "Jie Tang"
      }
    ],
    "citation-key": "arxiv_2312_08914",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "755198d83a3af9fe6d032f1446ec9bf57bf7e6f314d37787ce8a6aaa16bddc47",
        "submitted_at": "2023-12-14T13:20:57Z",
        "updated_at": "2024-12-27T06:56:18Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2312.08914v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2312.08914",
      "catalog_id": "arxiv:2312.08914",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "citation_edition": "record",
      "first_published_at": "2023-12-14",
      "identifiers": {
        "arxiv": "2312.08914"
      },
      "publication": {
        "authors": [
          "Wenyi Hong",
          "Weihan Wang",
          "Qingsong Lv",
          "Jiazheng Xu",
          "Wenmeng Yu",
          "Junhui Ji",
          "Yan Wang",
          "Zihan Wang",
          "Yuxiao Dong",
          "Ming Ding",
          "Jie Tang"
        ],
        "date_basis": "Year from publisher citation metadata and month from the same page's embedded BibTeX; no day is supplied.",
        "date_parts": [
          2024,
          6
        ],
        "doi": null,
        "event_dates": null,
        "evidence_urls": [
          "https://openaccess.thecvf.com/content/CVPR2024/html/Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper.html",
          "https://openaccess.thecvf.com/content/CVPR2024/papers/Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper.pdf"
        ],
        "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The publisher page directly links this arXiv identifier. The publisher PDF title and complete first-page author list were visually checked.",
        "issue": null,
        "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. The publisher PDF, page 1, and landing page list eleven authors; the retained arXiv snapshot lists fourteen. Each edition retains its own authors.",
        "pages": "14281-14290",
        "pdf_url": "https://openaccess.thecvf.com/content/CVPR2024/papers/Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper.pdf",
        "publisher": null,
        "series": null,
        "title": "CogAgent: A Visual Language Model for GUI Agents",
        "type": "conference-paper",
        "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper.html",
        "venue": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition",
        "volume": null
      },
      "record_updated_at": "2024-12-27"
    },
    "genre": "preprint",
    "id": "arxiv:2312.08914",
    "issued": {
      "date-parts": [
        [
          2023,
          12,
          14
        ]
      ]
    },
    "note": "First published: 2023-12-14; Recorded arXiv version: v3; Recorded version updated: 2024-12-27T06:56:18Z.",
    "title": "CogAgent: A Visual Language Model for GUI Agents",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2312.11190v2",
    "archive": "arXiv",
    "archive_location": "2312.11190",
    "author": [
      {
        "literal": "Yunpeng Song"
      },
      {
        "literal": "Yiheng Bian"
      },
      {
        "literal": "Yongtao Tang"
      },
      {
        "literal": "Guiyu Ma"
      },
      {
        "literal": "Zhongmin Cai"
      }
    ],
    "citation-key": "arxiv_2312_11190",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "df1390eab35db18dedaf135ddbbc9fdfcacbc9a70c51ec2609cf331cc05e06bd",
        "submitted_at": "2023-12-18T13:35:46Z",
        "updated_at": "2024-07-29T14:52:38Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2312.11190v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2312.11190",
      "catalog_id": "arxiv:2312.11190",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2023-12-18",
      "identifiers": {
        "arxiv": "2312.11190"
      },
      "record_updated_at": "2024-07-29"
    },
    "genre": "preprint",
    "id": "arxiv:2312.11190",
    "issued": {
      "date-parts": [
        [
          2023,
          12,
          18
        ]
      ]
    },
    "note": "First published: 2023-12-18; Recorded arXiv version: v2; Recorded version updated: 2024-07-29T14:52:38Z.",
    "title": "VisionTasker: Mobile Task Automation Using Vision Based UI Understanding and LLM Task Planning",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2402.04476v2",
    "archive": "arXiv",
    "archive_location": "2402.04476",
    "author": [
      {
        "literal": "Jihyung Kil"
      },
      {
        "literal": "Chan Hee Song"
      },
      {
        "literal": "Boyuan Zheng"
      },
      {
        "literal": "Xiang Deng"
      },
      {
        "literal": "Yu Su"
      },
      {
        "literal": "Wei-Lun Chao"
      }
    ],
    "citation-key": "arxiv_2402_04476",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "3da421fc440f7dcfc53d8ef218f55389e4da4dbac196f54b40402bc877ff0365",
        "submitted_at": "2024-02-06T23:52:10Z",
        "updated_at": "2024-03-30T05:18:05Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2402.04476v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2402.04476",
      "catalog_id": "arxiv:2402.04476",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-02-06",
      "identifiers": {
        "arxiv": "2402.04476"
      },
      "record_updated_at": "2024-03-30"
    },
    "genre": "preprint",
    "id": "arxiv:2402.04476",
    "issued": {
      "date-parts": [
        [
          2024,
          2,
          6
        ]
      ]
    },
    "note": "First published: 2024-02-06; Recorded arXiv version: v2; Recorded version updated: 2024-03-30T05:18:05Z.",
    "title": "Dual-View Visual Contextualization for Web Navigation",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2402.04615v3",
    "archive": "arXiv",
    "archive_location": "2402.04615",
    "author": [
      {
        "literal": "Gilles Baechler"
      },
      {
        "literal": "Srinivas Sunkara"
      },
      {
        "literal": "Maria Wang"
      },
      {
        "literal": "Fedir Zubach"
      },
      {
        "literal": "Hassan Mansoor"
      },
      {
        "literal": "Vincent Etter"
      },
      {
        "literal": "Victor Cărbune"
      },
      {
        "literal": "Jason Lin"
      },
      {
        "literal": "Jindong Chen"
      },
      {
        "literal": "Abhanshu Sharma"
      }
    ],
    "citation-key": "arxiv_2402_04615",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "b293ab33fe0f3607eccc2b99cbf06fb459792444433a4179bb65e081f33e426c",
        "submitted_at": "2024-02-07T06:42:33Z",
        "updated_at": "2024-07-04T07:08:15Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2402.04615v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2402.04615",
      "catalog_id": "arxiv:2402.04615",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-02-07",
      "identifiers": {
        "arxiv": "2402.04615"
      },
      "record_updated_at": "2024-07-04"
    },
    "genre": "preprint",
    "id": "arxiv:2402.04615",
    "issued": {
      "date-parts": [
        [
          2024,
          2,
          7
        ]
      ]
    },
    "note": "First published: 2024-02-07; Recorded arXiv version: v3; Recorded version updated: 2024-07-04T07:08:15Z.",
    "title": "ScreenAI: A Vision-Language Model for UI and Infographics Understanding",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2402.11941v3",
    "archive": "arXiv",
    "archive_location": "2402.11941",
    "author": [
      {
        "literal": "Xinbei Ma"
      },
      {
        "literal": "Zhuosheng Zhang"
      },
      {
        "literal": "Hai Zhao"
      }
    ],
    "citation-key": "arxiv_2402_11941",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "98930b10832d8169bdc60620f882b4b8f753440979c8e9a8de167b12d38d7060",
        "submitted_at": "2024-02-19T08:29:03Z",
        "updated_at": "2024-06-02T13:25:05Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2402.11941v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2402.11941",
      "catalog_id": "arxiv:2402.11941",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "citation_edition": "record",
      "first_published_at": "2024-02-19",
      "identifiers": {
        "arxiv": "2402.11941"
      },
      "publication": {
        "authors": [
          "Xinbei Ma",
          "Zhuosheng Zhang",
          "Hai Zhao (赵海)"
        ],
        "date_basis": "Explicit publisher citation_publication_date: 2024/8. Preserve supplied precision; do not substitute conference event dates.",
        "date_parts": [
          2024,
          8
        ],
        "doi": "10.18653/v1/2024.findings-acl.539",
        "event_dates": null,
        "evidence_urls": [
          "https://aclanthology.org/2024.findings-acl.539"
        ],
        "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.",
        "issue": null,
        "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.",
        "pages": "9097-9110",
        "pdf_url": "https://aclanthology.org/2024.findings-acl.539.pdf",
        "publisher": "Association for Computational Linguistics",
        "series": null,
        "title": "CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation",
        "type": "conference-paper",
        "url": "https://aclanthology.org/2024.findings-acl.539",
        "venue": "Findings of the Association for Computational Linguistics: ACL 2024",
        "volume": null
      },
      "record_updated_at": "2024-06-02"
    },
    "genre": "preprint",
    "id": "arxiv:2402.11941",
    "issued": {
      "date-parts": [
        [
          2024,
          2,
          19
        ]
      ]
    },
    "note": "First published: 2024-02-19; Recorded arXiv version: v3; Recorded version updated: 2024-06-02T13:25:05Z.",
    "title": "CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2402.14073v1",
    "archive": "arXiv",
    "archive_location": "2402.14073",
    "author": [
      {
        "literal": "Tianyu Gao"
      },
      {
        "literal": "Zirui Wang"
      },
      {
        "literal": "Adithya Bhaskar"
      },
      {
        "literal": "Danqi Chen"
      }
    ],
    "citation-key": "arxiv_2402_14073",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "0f3eed6e0021be438af9d056e97f71a838af905b948cfd6499423ab18df11e43",
        "submitted_at": "2024-02-21T19:01:03Z",
        "updated_at": "2024-02-21T19:01:03Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2402.14073v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2402.14073",
      "catalog_id": "arxiv:2402.14073",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "adjacent",
      "first_published_at": "2024-02-21",
      "identifiers": {
        "arxiv": "2402.14073"
      },
      "record_updated_at": "2024-02-21"
    },
    "genre": "preprint",
    "id": "arxiv:2402.14073",
    "issued": {
      "date-parts": [
        [
          2024,
          2,
          21
        ]
      ]
    },
    "note": "First published: 2024-02-21; Recorded arXiv version: v1; Recorded version updated: 2024-02-21T19:01:03Z.",
    "title": "Improving Language Understanding from Screenshots",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2403.03186v3",
    "archive": "arXiv",
    "archive_location": "2403.03186",
    "author": [
      {
        "literal": "Weihao Tan"
      },
      {
        "literal": "Wentao Zhang"
      },
      {
        "literal": "Xinrun Xu"
      },
      {
        "literal": "Haochong Xia"
      },
      {
        "literal": "Ziluo Ding"
      },
      {
        "literal": "Boyu Li"
      },
      {
        "literal": "Bohan Zhou"
      },
      {
        "literal": "Junpeng Yue"
      },
      {
        "literal": "Jiechuan Jiang"
      },
      {
        "literal": "Yewen Li"
      },
      {
        "literal": "Ruyi An"
      },
      {
        "literal": "Molei Qin"
      },
      {
        "literal": "Chuqiao Zong"
      },
      {
        "literal": "Longtao Zheng"
      },
      {
        "literal": "Yujie Wu"
      },
      {
        "literal": "Xiaoqiang Chai"
      },
      {
        "literal": "Yifei Bi"
      },
      {
        "literal": "Tianbao Xie"
      },
      {
        "literal": "Pengjie Gu"
      },
      {
        "literal": "Xiyun Li"
      },
      {
        "literal": "Ceyao Zhang"
      },
      {
        "literal": "Long Tian"
      },
      {
        "literal": "Chaojie Wang"
      },
      {
        "literal": "Xinrun Wang"
      },
      {
        "literal": "Börje F. Karlsson"
      },
      {
        "literal": "Bo An"
      },
      {
        "literal": "Shuicheng Yan"
      },
      {
        "literal": "Zongqing Lu"
      }
    ],
    "citation-key": "arxiv_2403_03186",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "63c68c596f1c81485e77f98beae696deca9785a5d8725ab4456ee35870e64a99",
        "submitted_at": "2024-03-05T18:22:29Z",
        "updated_at": "2024-07-02T17:23:13Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2403.03186v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2403.03186",
      "catalog_id": "arxiv:2403.03186",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "citation_edition": "record",
      "first_published_at": "2024-03-05",
      "identifiers": {
        "arxiv": "2403.03186"
      },
      "publication": {
        "authors": [
          "Weihao Tan",
          "Wentao Zhang",
          "Xinrun Xu",
          "Haochong Xia",
          "Ziluo Ding",
          "Boyu Li",
          "Bohan Zhou",
          "Junpeng Yue",
          "Jiechuan Jiang",
          "Yewen Li",
          "Ruyi An",
          "Molei Qin",
          "Chuqiao Zong",
          "Longtao Zheng",
          "Yujie Wu",
          "Xiaoqiang Chai",
          "Yifei Bi",
          "Tianbao Xie",
          "Pengjie Gu",
          "Xiyun Li",
          "Ceyao Zhang",
          "Long Tian",
          "Chaojie Wang",
          "Xinrun Wang",
          "Börje F. Karlsson",
          "Bo An",
          "Shuicheng Yan",
          "Zongqing Lu"
        ],
        "date_basis": "Explicit publisher metadata: 2025/10/06; precision=day.",
        "date_parts": [
          2025,
          10,
          6
        ],
        "doi": null,
        "event_dates": "13--19 Jul 2025",
        "evidence_urls": [
          "https://proceedings.mlr.press/v267/tan25h.html"
        ],
        "identity_basis": "Same work: exact normalized landing title, corresponding author list, and matching specific contribution. Publisher and arXiv versions remain distinct.",
        "issue": null,
        "notes": "The publisher issue date comes from citation_publication_date; the conference date range is retained separately and does not replace it. Publisher-hosted proceedings record; distinct from the retained arXiv preprint snapshot.",
        "pages": "58658-58725",
        "pdf_url": "https://raw.githubusercontent.com/mlresearch/v267/main/assets/tan25h/tan25h.pdf",
        "publisher": "PMLR",
        "series": "Proceedings of Machine Learning Research",
        "title": "Cradle: Empowering Foundation Agents towards General Computer Control",
        "type": "conference-paper",
        "url": "https://proceedings.mlr.press/v267/tan25h.html",
        "venue": "Proceedings of the 42nd International Conference on Machine Learning",
        "volume": "267"
      },
      "record_updated_at": "2024-07-02"
    },
    "genre": "preprint",
    "id": "arxiv:2403.03186",
    "issued": {
      "date-parts": [
        [
          2024,
          3,
          5
        ]
      ]
    },
    "note": "First published: 2024-03-05; Recorded arXiv version: v3; Recorded version updated: 2024-07-02T17:23:13Z.",
    "title": "Cradle: Empowering Foundation Agents Towards General Computer Control",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2403.04984v1",
    "archive": "arXiv",
    "archive_location": "2403.04984",
    "author": [
      {
        "literal": "Shuhong Xiao"
      },
      {
        "literal": "Yunnong Chen"
      },
      {
        "literal": "Yaxuan Song"
      },
      {
        "literal": "Liuqing Chen"
      },
      {
        "literal": "Lingyun Sun"
      },
      {
        "literal": "Yankun Zhen"
      },
      {
        "literal": "Yanfang Chang"
      }
    ],
    "citation-key": "arxiv_2403_04984",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "f4bfed18cba0c946a8ae013c819d84d7f7b2c639b2e3471d6bf7890248c4530b",
        "submitted_at": "2024-03-08T01:52:44Z",
        "updated_at": "2024-03-08T01:52:44Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2403.04984v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2403.04984",
      "catalog_id": "arxiv:2403.04984",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-03-08",
      "identifiers": {
        "arxiv": "2403.04984"
      },
      "record_updated_at": "2024-03-08"
    },
    "genre": "preprint",
    "id": "arxiv:2403.04984",
    "issued": {
      "date-parts": [
        [
          2024,
          3,
          8
        ]
      ]
    },
    "note": "First published: 2024-03-08; Recorded arXiv version: v1; Recorded version updated: 2024-03-08T01:52:44Z.",
    "title": "UI Semantic Group Detection: Grouping UI Elements with Similar Semantics in Mobile Graphical User Interface",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2403.10170v2",
    "archive": "arXiv",
    "archive_location": "2403.10170",
    "author": [
      {
        "literal": "Andrés Muñoz"
      },
      {
        "literal": "Daniel Borrajo"
      }
    ],
    "citation-key": "arxiv_2403_10170",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "aacb4d2cac31e478aa56ee25b6b39e5ba8fe164f89102e665f8fb25cf3822e7b",
        "submitted_at": "2024-03-15T10:26:52Z",
        "updated_at": "2024-08-27T18:36:12Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2403.10170v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2403.10170",
      "catalog_id": "arxiv:2403.10170",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-03-15",
      "identifiers": {
        "arxiv": "2403.10170"
      },
      "record_updated_at": "2024-08-27"
    },
    "genre": "preprint",
    "id": "arxiv:2403.10170",
    "issued": {
      "date-parts": [
        [
          2024,
          3,
          15
        ]
      ]
    },
    "note": "First published: 2024-03-15; Recorded arXiv version: v2; Recorded version updated: 2024-08-27T18:36:12Z.",
    "title": "Computer User Interface Understanding. A New Dataset and a Learning Framework",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2403.20329v2",
    "archive": "arXiv",
    "archive_location": "2403.20329",
    "author": [
      {
        "literal": "Joel Ruben Antony Moniz"
      },
      {
        "literal": "Soundarya Krishnan"
      },
      {
        "literal": "Melis Ozyildirim"
      },
      {
        "literal": "Prathamesh Saraf"
      },
      {
        "literal": "Halim Cagri Ates"
      },
      {
        "literal": "Yuan Zhang"
      },
      {
        "literal": "Hong Yu"
      }
    ],
    "citation-key": "arxiv_2403_20329",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "a3573a5cf66737178f164d9809b3e6dcadb7c6b2b4ae7d95283e8a136bf78851",
        "submitted_at": "2024-03-29T17:59:06Z",
        "updated_at": "2024-08-19T03:06:24Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2403.20329v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2403.20329",
      "catalog_id": "arxiv:2403.20329",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "adjacent",
      "first_published_at": "2024-03-29",
      "identifiers": {
        "arxiv": "2403.20329"
      },
      "record_updated_at": "2024-08-19"
    },
    "genre": "preprint",
    "id": "arxiv:2403.20329",
    "issued": {
      "date-parts": [
        [
          2024,
          3,
          29
        ]
      ]
    },
    "note": "First published: 2024-03-29; Recorded arXiv version: v2; Recorded version updated: 2024-08-19T03:06:24Z.",
    "title": "ReALM: Reference Resolution As Language Modeling",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2404.05719v1",
    "archive": "arXiv",
    "archive_location": "2404.05719",
    "author": [
      {
        "literal": "Keen You"
      },
      {
        "literal": "Haotian Zhang"
      },
      {
        "literal": "Eldon Schoop"
      },
      {
        "literal": "Floris Weers"
      },
      {
        "literal": "Amanda Swearngin"
      },
      {
        "literal": "Jeffrey Nichols"
      },
      {
        "literal": "Yinfei Yang"
      },
      {
        "literal": "Zhe Gan"
      }
    ],
    "citation-key": "arxiv_2404_05719",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "67e139ad83ab4804dfdc4c91f3fd344d7d3d279b97efb25bd11bab1532968e46",
        "submitted_at": "2024-04-08T17:55:44Z",
        "updated_at": "2024-04-08T17:55:44Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2404.05719v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2404.05719",
      "catalog_id": "arxiv:2404.05719",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-04-08",
      "identifiers": {
        "arxiv": "2404.05719"
      },
      "record_updated_at": "2024-04-08"
    },
    "genre": "preprint",
    "id": "arxiv:2404.05719",
    "issued": {
      "date-parts": [
        [
          2024,
          4,
          8
        ]
      ]
    },
    "note": "First published: 2024-04-08; Recorded arXiv version: v1; Recorded version updated: 2024-04-08T17:55:44Z.",
    "title": "Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2404.05955v1",
    "archive": "arXiv",
    "archive_location": "2404.05955",
    "author": [
      {
        "literal": "Junpeng Liu"
      },
      {
        "literal": "Yifan Song"
      },
      {
        "literal": "Bill Yuchen Lin"
      },
      {
        "literal": "Wai Lam"
      },
      {
        "literal": "Graham Neubig"
      },
      {
        "literal": "Yuanzhi Li"
      },
      {
        "literal": "Xiang Yue"
      }
    ],
    "citation-key": "arxiv_2404_05955",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "7414bfa289baf86a8f2bb54f3f69f25a6a4cc8516fb0296a1899d21ad3020d4f",
        "submitted_at": "2024-04-09T02:29:39Z",
        "updated_at": "2024-04-09T02:29:39Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2404.05955v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2404.05955",
      "catalog_id": "arxiv:2404.05955",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-04-09",
      "identifiers": {
        "arxiv": "2404.05955"
      },
      "record_updated_at": "2024-04-09"
    },
    "genre": "preprint",
    "id": "arxiv:2404.05955",
    "issued": {
      "date-parts": [
        [
          2024,
          4,
          9
        ]
      ]
    },
    "note": "First published: 2024-04-09; Recorded arXiv version: v1; Recorded version updated: 2024-04-09T02:29:39Z.",
    "title": "VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2405.07090v1",
    "archive": "arXiv",
    "archive_location": "2405.07090",
    "author": [
      {
        "literal": "Sidong Feng"
      },
      {
        "literal": "Suyu Ma"
      },
      {
        "literal": "Han Wang"
      },
      {
        "literal": "David Kong"
      },
      {
        "literal": "Chunyang Chen"
      }
    ],
    "citation-key": "arxiv_2405_07090",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "d200a997596ea919d5210b5ca5760241f9dfa3ad581e090a541871cd6e117522",
        "submitted_at": "2024-05-11T20:32:16Z",
        "updated_at": "2024-05-11T20:32:16Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2405.07090v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2405.07090",
      "catalog_id": "arxiv:2405.07090",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-05-11",
      "identifiers": {
        "arxiv": "2405.07090"
      },
      "record_updated_at": "2024-05-11"
    },
    "genre": "preprint",
    "id": "arxiv:2405.07090",
    "issued": {
      "date-parts": [
        [
          2024,
          5,
          11
        ]
      ]
    },
    "note": "First published: 2024-05-11; Recorded arXiv version: v1; Recorded version updated: 2024-05-11T20:32:16Z.",
    "title": "MUD: Towards a Large-Scale and Noise-Filtered UI Dataset for Modern Style UI Modeling",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2405.12842v1",
    "archive": "arXiv",
    "archive_location": "2405.12842",
    "author": [
      {
        "literal": "Arushi Jain"
      },
      {
        "literal": "Shubham Paliwal"
      },
      {
        "literal": "Monika Sharma"
      },
      {
        "literal": "Lovekesh Vig"
      },
      {
        "literal": "Gautam Shroff"
      }
    ],
    "citation-key": "arxiv_2405_12842",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "ca8d7e7dc3a537573ac3990d532589cdca12bf441ee40521cc46044fd10c5263",
        "submitted_at": "2024-05-21T14:49:12Z",
        "updated_at": "2024-05-21T14:49:12Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2405.12842v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2405.12842",
      "catalog_id": "arxiv:2405.12842",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-05-21",
      "identifiers": {
        "arxiv": "2405.12842"
      },
      "record_updated_at": "2024-05-21"
    },
    "genre": "preprint",
    "id": "arxiv:2405.12842",
    "issued": {
      "date-parts": [
        [
          2024,
          5,
          21
        ]
      ]
    },
    "note": "First published: 2024-05-21; Recorded arXiv version: v1; Recorded version updated: 2024-05-21T14:49:12Z.",
    "title": "SmartFlow: Robotic Process Automation using LLMs",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2405.15341v2",
    "archive": "arXiv",
    "archive_location": "2405.15341",
    "author": [
      {
        "literal": "Abdur Rahman"
      },
      {
        "literal": "Rajat Chawla"
      },
      {
        "literal": "Muskaan Kumar"
      },
      {
        "literal": "Arkajit Datta"
      },
      {
        "literal": "Adarsh Jha"
      },
      {
        "literal": "Mukunda NS"
      },
      {
        "literal": "Ishaan Bhola"
      }
    ],
    "citation-key": "arxiv_2405_15341",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "e7cb6087a48596442e1d191bf1313e9459ad62c02c3104ee481cb72cb00e56b1",
        "submitted_at": "2024-05-24T08:21:45Z",
        "updated_at": "2024-07-21T07:34:44Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2405.15341v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2405.15341",
      "catalog_id": "arxiv:2405.15341",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-05-24",
      "identifiers": {
        "arxiv": "2405.15341"
      },
      "record_updated_at": "2024-07-21"
    },
    "genre": "preprint",
    "id": "arxiv:2405.15341",
    "issued": {
      "date-parts": [
        [
          2024,
          5,
          24
        ]
      ]
    },
    "note": "First published: 2024-05-24; Recorded arXiv version: v2; Recorded version updated: 2024-07-21T07:34:44Z.",
    "title": "V-Zen: Efficient GUI Understanding and Precise Grounding With A Novel Multimodal LLM",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2406.06947v3",
    "archive": "arXiv",
    "archive_location": "2406.06947",
    "author": [
      {
        "literal": "Junhee Cho"
      },
      {
        "literal": "Jihoon Kim"
      },
      {
        "literal": "Daseul Bae"
      },
      {
        "literal": "Jinho Choo"
      },
      {
        "literal": "Youngjune Gwon"
      },
      {
        "literal": "Yeong-Dae Kwon"
      }
    ],
    "citation-key": "arxiv_2406_06947",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "5f85b2cf7650f41ba9ee6e4ae83cd9041e077a44adcb685e702d644bd5779963",
        "submitted_at": "2024-06-11T05:21:20Z",
        "updated_at": "2024-12-26T11:02:28Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2406.06947v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2406.06947",
      "catalog_id": "arxiv:2406.06947",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-06-11",
      "identifiers": {
        "arxiv": "2406.06947"
      },
      "record_updated_at": "2024-12-26"
    },
    "genre": "preprint",
    "id": "arxiv:2406.06947",
    "issued": {
      "date-parts": [
        [
          2024,
          6,
          11
        ]
      ]
    },
    "note": "First published: 2024-06-11; Recorded arXiv version: v3; Recorded version updated: 2024-12-26T11:02:28Z.",
    "title": "CAAP: Context-Aware Action Planning Prompting to Solve Computer Tasks with Front-End UI Only",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2406.07822v2",
    "archive": "arXiv",
    "archive_location": "2406.07822",
    "author": [
      {
        "literal": "Andrea Burns"
      },
      {
        "literal": "Kate Saenko"
      },
      {
        "literal": "Bryan A. Plummer"
      }
    ],
    "citation-key": "arxiv_2406_07822",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "47d0ca0467a104f9b8be037ec73131f12b66a22b0a89fe975bec7680073c8f39",
        "submitted_at": "2024-06-12T02:43:19Z",
        "updated_at": "2024-08-08T02:36:04Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2406.07822v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2406.07822",
      "catalog_id": "arxiv:2406.07822",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-06-12",
      "identifiers": {
        "arxiv": "2406.07822"
      },
      "record_updated_at": "2024-08-08"
    },
    "genre": "preprint",
    "id": "arxiv:2406.07822",
    "issued": {
      "date-parts": [
        [
          2024,
          6,
          12
        ]
      ]
    },
    "note": "First published: 2024-06-12; Recorded arXiv version: v2; Recorded version updated: 2024-08-08T02:36:04Z.",
    "title": "Tell Me What's Next: Textual Foresight for Generic UI Representations",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2406.08340v1",
    "archive": "arXiv",
    "archive_location": "2406.08340",
    "author": [
      {
        "literal": "Shengcheng Yu"
      },
      {
        "literal": "Chunrong Fang"
      },
      {
        "literal": "Mingzhe Du"
      },
      {
        "literal": "Zimin Ding"
      },
      {
        "literal": "Zhenyu Chen"
      },
      {
        "literal": "Zhendong Su"
      }
    ],
    "citation-key": "arxiv_2406_08340",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "0061e9004afe11bf188164ea37de1acd15e1b95ae2fcad22044264a89e4636b3",
        "submitted_at": "2024-06-12T15:48:39Z",
        "updated_at": "2024-06-12T15:48:39Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2406.08340v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2406.08340",
      "catalog_id": "arxiv:2406.08340",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-06-12",
      "identifiers": {
        "arxiv": "2406.08340"
      },
      "record_updated_at": "2024-06-12"
    },
    "genre": "preprint",
    "id": "arxiv:2406.08340",
    "issued": {
      "date-parts": [
        [
          2024,
          6,
          12
        ]
      ]
    },
    "note": "First published: 2024-06-12; Recorded arXiv version: v1; Recorded version updated: 2024-06-12T15:48:39Z.",
    "title": "Practical, Automated Scenario-based Mobile App Testing",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2406.10819v2",
    "archive": "arXiv",
    "archive_location": "2406.10819",
    "author": [
      {
        "literal": "Dongping Chen"
      },
      {
        "literal": "Yue Huang"
      },
      {
        "literal": "Siyuan Wu"
      },
      {
        "literal": "Jingyu Tang"
      },
      {
        "literal": "Liuyi Chen"
      },
      {
        "literal": "Yilin Bai"
      },
      {
        "literal": "Zhigang He"
      },
      {
        "literal": "Chenlong Wang"
      },
      {
        "literal": "Huichi Zhou"
      },
      {
        "literal": "Yiqiang Li"
      },
      {
        "literal": "Tianshuo Zhou"
      },
      {
        "literal": "Yue Yu"
      },
      {
        "literal": "Chujie Gao"
      },
      {
        "literal": "Qihui Zhang"
      },
      {
        "literal": "Yi Gui"
      },
      {
        "literal": "Zhen Li"
      },
      {
        "literal": "Yao Wan"
      },
      {
        "literal": "Pan Zhou"
      },
      {
        "literal": "Jianfeng Gao"
      },
      {
        "literal": "Lichao Sun"
      }
    ],
    "citation-key": "arxiv_2406_10819",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "9997c3ab43f0e3e69ad4dcbe15257ea4392d36fa3c82f90c6b7730667a067f99",
        "submitted_at": "2024-06-16T06:56:53Z",
        "updated_at": "2025-03-24T11:46:14Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2406.10819v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2406.10819",
      "catalog_id": "arxiv:2406.10819",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-06-16",
      "identifiers": {
        "arxiv": "2406.10819"
      },
      "record_updated_at": "2025-03-24"
    },
    "genre": "preprint",
    "id": "arxiv:2406.10819",
    "issued": {
      "date-parts": [
        [
          2024,
          6,
          16
        ]
      ]
    },
    "note": "First published: 2024-06-16; Recorded arXiv version: v2; Recorded version updated: 2025-03-24T11:46:14Z.",
    "title": "GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2406.11317v2",
    "archive": "arXiv",
    "archive_location": "2406.11317",
    "author": [
      {
        "literal": "Wentong Chen"
      },
      {
        "literal": "Junbo Cui"
      },
      {
        "literal": "Jinyi Hu"
      },
      {
        "literal": "Yujia Qin"
      },
      {
        "literal": "Junjie Fang"
      },
      {
        "literal": "Yue Zhao"
      },
      {
        "literal": "Chongyi Wang"
      },
      {
        "literal": "Jun Liu"
      },
      {
        "literal": "Guirong Chen"
      },
      {
        "literal": "Yupeng Huo"
      },
      {
        "literal": "Yuan Yao"
      },
      {
        "literal": "Yankai Lin"
      },
      {
        "literal": "Zhiyuan Liu"
      },
      {
        "literal": "Maosong Sun"
      }
    ],
    "citation-key": "arxiv_2406_11317",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "40e41704dbe59f1fb9b1e743a3c13394105de112213f666c2420fb235d666ef3",
        "submitted_at": "2024-06-17T08:30:55Z",
        "updated_at": "2025-05-30T07:30:07Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2406.11317v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2406.11317",
      "catalog_id": "arxiv:2406.11317",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-06-17",
      "identifiers": {
        "arxiv": "2406.11317"
      },
      "record_updated_at": "2025-05-30"
    },
    "genre": "preprint",
    "id": "arxiv:2406.11317",
    "issued": {
      "date-parts": [
        [
          2024,
          6,
          17
        ]
      ]
    },
    "note": "First published: 2024-06-17; Recorded arXiv version: v2; Recorded version updated: 2025-05-30T07:30:07Z.",
    "title": "GUICourse: From General Vision Language Models to Versatile GUI Agents",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2406.13719v1",
    "archive": "arXiv",
    "archive_location": "2406.13719",
    "author": [
      {
        "literal": "Qinchen Wu"
      },
      {
        "literal": "Difei Gao"
      },
      {
        "literal": "Kevin Qinghong Lin"
      },
      {
        "literal": "Zhuoyu Wu"
      },
      {
        "literal": "Xiangwu Guo"
      },
      {
        "literal": "Peiran Li"
      },
      {
        "literal": "Weichen Zhang"
      },
      {
        "literal": "Hengxu Wang"
      },
      {
        "literal": "Mike Zheng Shou"
      }
    ],
    "citation-key": "arxiv_2406_13719",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "369c32dba4bab0cfc05b41db16c73d5672605b7f81caabb2dbd72f581b3290ec",
        "submitted_at": "2024-06-19T17:22:11Z",
        "updated_at": "2024-06-19T17:22:11Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2406.13719v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2406.13719",
      "catalog_id": "arxiv:2406.13719",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-06-19",
      "identifiers": {
        "arxiv": "2406.13719"
      },
      "record_updated_at": "2024-06-19"
    },
    "genre": "preprint",
    "id": "arxiv:2406.13719",
    "issued": {
      "date-parts": [
        [
          2024,
          6,
          19
        ]
      ]
    },
    "note": "First published: 2024-06-19; Recorded arXiv version: v1; Recorded version updated: 2024-06-19T17:22:11Z.",
    "title": "GUI Action Narrator: Where and When Did That Action Take Place?",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2406.14056v3",
    "archive": "arXiv",
    "archive_location": "2406.14056",
    "author": [
      {
        "literal": "Ziyang Meng"
      },
      {
        "literal": "Yu Dai"
      },
      {
        "literal": "Zezheng Gong"
      },
      {
        "literal": "Shaoxiong Guo"
      },
      {
        "literal": "Minglong Tang"
      },
      {
        "literal": "Tongquan Wei"
      }
    ],
    "citation-key": "arxiv_2406_14056",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "ea674b3aec3aee51c6f7fd4e99ad2b88394e7df43a4f3a02654d805e9a60343a",
        "submitted_at": "2024-06-20T07:24:43Z",
        "updated_at": "2024-11-04T09:31:06Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2406.14056v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2406.14056",
      "catalog_id": "arxiv:2406.14056",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "citation_edition": "record",
      "first_published_at": "2024-06-20",
      "identifiers": {
        "arxiv": "2406.14056"
      },
      "publication": {
        "authors": [
          "Meng Ziyang",
          "Yu Dai",
          "Zezheng Gong",
          "Shaoxiong Guo",
          "Minglong Tang",
          "Tongquan Wei"
        ],
        "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.",
        "date_parts": [
          2024,
          11
        ],
        "doi": "10.18653/v1/2024.findings-emnlp.68",
        "event_dates": null,
        "evidence_urls": [
          "https://aclanthology.org/2024.findings-emnlp.68/"
        ],
        "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.",
        "issue": null,
        "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint.",
        "pages": "1261-1279",
        "pdf_url": "https://aclanthology.org/2024.findings-emnlp.68.pdf",
        "publisher": "Association for Computational Linguistics",
        "series": null,
        "title": "VGA: Vision GUI Assistant - Minimizing Hallucinations through Image-Centric Fine-Tuning",
        "type": "conference-paper",
        "url": "https://aclanthology.org/2024.findings-emnlp.68/",
        "venue": "Findings of the Association for Computational Linguistics: EMNLP 2024",
        "volume": null
      },
      "record_updated_at": "2024-11-04"
    },
    "genre": "preprint",
    "id": "arxiv:2406.14056",
    "issued": {
      "date-parts": [
        [
          2024,
          6,
          20
        ]
      ]
    },
    "note": "First published: 2024-06-20; Recorded arXiv version: v3; Recorded version updated: 2024-11-04T09:31:06Z.",
    "title": "VGA: Vision GUI Assistant -- Minimizing Hallucinations through Image-Centric Fine-Tuning",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2406.14314v3",
    "archive": "arXiv",
    "archive_location": "2406.14314",
    "author": [
      {
        "literal": "Omri Berkovitch"
      },
      {
        "literal": "Sapir Caduri"
      },
      {
        "literal": "Noam Kahlon"
      },
      {
        "literal": "Anatoly Efros"
      },
      {
        "literal": "Avi Caciularu"
      },
      {
        "literal": "Ido Dagan"
      }
    ],
    "citation-key": "arxiv_2406_14314",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "a0bc798b69e59d1ec0ca8ecb0fab7a7ee6594f4d656ca4212b19be7e3085c0c5",
        "submitted_at": "2024-06-20T13:46:10Z",
        "updated_at": "2025-03-03T15:47:10Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2406.14314v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2406.14314",
      "catalog_id": "arxiv:2406.14314",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-06-20",
      "identifiers": {
        "arxiv": "2406.14314"
      },
      "record_updated_at": "2025-03-03"
    },
    "genre": "preprint",
    "id": "arxiv:2406.14314",
    "issued": {
      "date-parts": [
        [
          2024,
          6,
          20
        ]
      ]
    },
    "note": "First published: 2024-06-20; Recorded arXiv version: v3; Recorded version updated: 2025-03-03T15:47:10Z.",
    "title": "Identifying User Goals from UI Trajectories",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2406.19263v2",
    "archive": "arXiv",
    "archive_location": "2406.19263",
    "author": [
      {
        "literal": "Yue Fan"
      },
      {
        "literal": "Lei Ding"
      },
      {
        "literal": "Ching-Chen Kuo"
      },
      {
        "literal": "Shan Jiang"
      },
      {
        "literal": "Yang Zhao"
      },
      {
        "literal": "Xinze Guan"
      },
      {
        "literal": "Jie Yang"
      },
      {
        "literal": "Yi Zhang"
      },
      {
        "literal": "Xin Eric Wang"
      }
    ],
    "citation-key": "arxiv_2406_19263",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "0c86d68b5c3486b099f64792d5d3290d79e25b7c82c6eb2402869b893bb22fea",
        "submitted_at": "2024-06-27T15:34:16Z",
        "updated_at": "2024-10-25T18:16:21Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2406.19263v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2406.19263",
      "catalog_id": "arxiv:2406.19263",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "citation_edition": "record",
      "first_published_at": "2024-06-27",
      "identifiers": {
        "arxiv": "2406.19263"
      },
      "publication": {
        "authors": [
          "Yue Fan",
          "Lei Ding",
          "Ching-Chen Kuo",
          "Shan Jiang",
          "Yang Zhao",
          "Xinze Guan",
          "Jie Yang",
          "Yi Zhang",
          "Xin Eric Wang"
        ],
        "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.",
        "date_parts": [
          2024,
          11
        ],
        "doi": "10.18653/v1/2024.emnlp-main.533",
        "event_dates": null,
        "evidence_urls": [
          "https://aclanthology.org/2024.emnlp-main.533/"
        ],
        "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.",
        "issue": null,
        "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.",
        "pages": "9503-9522",
        "pdf_url": "https://aclanthology.org/2024.emnlp-main.533.pdf",
        "publisher": "Association for Computational Linguistics",
        "series": null,
        "title": "Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding",
        "type": "conference-paper",
        "url": "https://aclanthology.org/2024.emnlp-main.533/",
        "venue": "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
        "volume": null
      },
      "record_updated_at": "2024-10-25"
    },
    "genre": "preprint",
    "id": "arxiv:2406.19263",
    "issued": {
      "date-parts": [
        [
          2024,
          6,
          27
        ]
      ]
    },
    "note": "First published: 2024-06-27; Recorded arXiv version: v2; Recorded version updated: 2024-10-25T18:16:21Z.",
    "title": "Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2407.03037v2",
    "archive": "arXiv",
    "archive_location": "2407.03037",
    "author": [
      {
        "literal": "Zhe Liu"
      },
      {
        "literal": "Cheng Li"
      },
      {
        "literal": "Chunyang Chen"
      },
      {
        "literal": "Junjie Wang"
      },
      {
        "literal": "Mengzhuo Chen"
      },
      {
        "literal": "Boyu Wu"
      },
      {
        "literal": "Yawen Wang"
      },
      {
        "literal": "Jun Hu"
      },
      {
        "literal": "Qing Wang"
      }
    ],
    "citation-key": "arxiv_2407_03037",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "73b706ac6089a7d19836268437f3fea58d10b9d170ac596ac0d5a12f0d3a9668",
        "submitted_at": "2024-07-03T11:58:09Z",
        "updated_at": "2024-12-04T08:00:42Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2407.03037v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2407.03037",
      "catalog_id": "arxiv:2407.03037",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-07-03",
      "identifiers": {
        "arxiv": "2407.03037"
      },
      "record_updated_at": "2024-12-04"
    },
    "genre": "preprint",
    "id": "arxiv:2407.03037",
    "issued": {
      "date-parts": [
        [
          2024,
          7,
          3
        ]
      ]
    },
    "note": "First published: 2024-07-03; Recorded arXiv version: v2; Recorded version updated: 2024-12-04T08:00:42Z.",
    "title": "Seeing is Believing: Vision-driven Non-crash Functional Bug Detection for Mobile Apps",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2407.04346v3",
    "archive": "arXiv",
    "archive_location": "2407.04346",
    "author": [
      {
        "literal": "Songqin Nong"
      },
      {
        "literal": "Jiali Zhu"
      },
      {
        "literal": "Rui Wu"
      },
      {
        "literal": "Jiongchao Jin"
      },
      {
        "literal": "Shuo Shan"
      },
      {
        "literal": "Xiutian Huang"
      },
      {
        "literal": "Wenhao Xu"
      }
    ],
    "citation-key": "arxiv_2407_04346",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "59708ce4edeba4e913ae890f458b51907dd2f3b0b10bb18c86469b36375c84e4",
        "submitted_at": "2024-07-05T08:37:10Z",
        "updated_at": "2024-12-06T07:43:34Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2407.04346v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2407.04346",
      "catalog_id": "arxiv:2407.04346",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-07-05",
      "identifiers": {
        "arxiv": "2407.04346"
      },
      "record_updated_at": "2024-12-06"
    },
    "genre": "preprint",
    "id": "arxiv:2407.04346",
    "issued": {
      "date-parts": [
        [
          2024,
          7,
          5
        ]
      ]
    },
    "note": "First published: 2024-07-05; Recorded arXiv version: v3; Recorded version updated: 2024-12-06T07:43:34Z.",
    "title": "MobileFlow: A Multimodal LLM For Mobile GUI Agent",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2407.08850v3",
    "archive": "arXiv",
    "archive_location": "2407.08850",
    "author": [
      {
        "literal": "Peitong Duan"
      },
      {
        "literal": "Chin-yi Chen"
      },
      {
        "literal": "Gang Li"
      },
      {
        "literal": "Bjoern Hartmann"
      },
      {
        "literal": "Yang Li"
      }
    ],
    "citation-key": "arxiv_2407_08850",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "390a7415ad5f665de43f7d294e0a575785ef7e2810dead3363632174b2986af4",
        "submitted_at": "2024-07-11T20:18:19Z",
        "updated_at": "2024-08-13T23:41:43Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2407.08850v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2407.08850",
      "catalog_id": "arxiv:2407.08850",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "adjacent",
      "first_published_at": "2024-07-11",
      "identifiers": {
        "arxiv": "2407.08850"
      },
      "record_updated_at": "2024-08-13"
    },
    "genre": "preprint",
    "id": "arxiv:2407.08850",
    "issued": {
      "date-parts": [
        [
          2024,
          7,
          11
        ]
      ]
    },
    "note": "First published: 2024-07-11; Recorded arXiv version: v3; Recorded version updated: 2024-08-13T23:41:43Z.",
    "title": "UICrit: Enhancing Automated Design Evaluation with a UICritique Dataset",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2407.17490v2",
    "archive": "arXiv",
    "archive_location": "2407.17490",
    "author": [
      {
        "literal": "Yuxiang Chai"
      },
      {
        "literal": "Siyuan Huang"
      },
      {
        "literal": "Yazhe Niu"
      },
      {
        "literal": "Han Xiao"
      },
      {
        "literal": "Liang Liu"
      },
      {
        "literal": "Dingyu Zhang"
      },
      {
        "literal": "Shuai Ren"
      },
      {
        "literal": "Hongsheng Li"
      }
    ],
    "citation-key": "arxiv_2407_17490",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "9c80665716bf665fe4688a27a4c7dcf26fcfe93cb7f79a6f28784a795e0bd3cb",
        "submitted_at": "2024-07-03T17:59:58Z",
        "updated_at": "2025-05-29T02:43:50Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2407.17490v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2407.17490",
      "catalog_id": "arxiv:2407.17490",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "citation_edition": "record",
      "first_published_at": "2024-07-03",
      "identifiers": {
        "arxiv": "2407.17490"
      },
      "publication": {
        "authors": [
          "Yuxiang Chai",
          "Siyuan Huang",
          "Yazhe Niu",
          "Han Xiao",
          "Liang Liu",
          "Guozhi Wang",
          "Dingyu Zhang",
          "Shuai Ren",
          "Hongsheng Li"
        ],
        "date_basis": "Explicit publisher citation_publication_date: 2025/7. Preserve supplied precision; do not substitute conference event dates.",
        "date_parts": [
          2025,
          7
        ],
        "doi": "10.18653/v1/2025.findings-acl.110",
        "event_dates": null,
        "evidence_urls": [
          "https://aclanthology.org/2025.findings-acl.110/",
          "https://aclanthology.org/2025.findings-acl.110.pdf"
        ],
        "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The publisher PDF title and complete first-page author list were visually checked.",
        "issue": null,
        "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. The publisher PDF, page 1, lists nine authors including Guozhi Wang; the retained arXiv snapshot lists eight. Each edition retains its own authors.",
        "pages": "2138-2156",
        "pdf_url": "https://aclanthology.org/2025.findings-acl.110.pdf",
        "publisher": "Association for Computational Linguistics",
        "series": null,
        "title": "AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents",
        "type": "conference-paper",
        "url": "https://aclanthology.org/2025.findings-acl.110/",
        "venue": "Findings of the Association for Computational Linguistics: ACL 2025",
        "volume": null
      },
      "record_updated_at": "2025-05-29"
    },
    "genre": "preprint",
    "id": "arxiv:2407.17490",
    "issued": {
      "date-parts": [
        [
          2024,
          7,
          3
        ]
      ]
    },
    "note": "First published: 2024-07-03; Recorded arXiv version: v2; Recorded version updated: 2025-05-29T02:43:50Z.",
    "title": "AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2408.00203v1",
    "archive": "arXiv",
    "archive_location": "2408.00203",
    "author": [
      {
        "literal": "Yadong Lu"
      },
      {
        "literal": "Jianwei Yang"
      },
      {
        "literal": "Yelong Shen"
      },
      {
        "literal": "Ahmed Awadallah"
      }
    ],
    "citation-key": "arxiv_2408_00203",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "dfe55dd83d2f5ac48f9e3efb6bdf4aab7f11d81c0118725555456cce276adae3",
        "submitted_at": "2024-08-01T00:00:43Z",
        "updated_at": "2024-08-01T00:00:43Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2408.00203v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2408.00203",
      "catalog_id": "arxiv:2408.00203",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-08-01",
      "identifiers": {
        "arxiv": "2408.00203"
      },
      "record_updated_at": "2024-08-01"
    },
    "genre": "preprint",
    "id": "arxiv:2408.00203",
    "issued": {
      "date-parts": [
        [
          2024,
          8,
          1
        ]
      ]
    },
    "note": "First published: 2024-08-01; Recorded arXiv version: v1; Recorded version updated: 2024-08-01T00:00:43Z.",
    "title": "OmniParser for Pure Vision Based GUI Agent",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2409.09354v1",
    "archive": "arXiv",
    "archive_location": "2409.09354",
    "author": [
      {
        "literal": "Kelin Fu"
      },
      {
        "literal": "Yang Tian"
      },
      {
        "literal": "Kaigui Bian"
      }
    ],
    "citation-key": "arxiv_2409_09354",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "b46dabe4135f0caca15d54f84cfe805cdb7fe7f1abcce6b004483d99eb21e637",
        "submitted_at": "2024-09-14T07:54:25Z",
        "updated_at": "2024-09-14T07:54:25Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2409.09354v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2409.09354",
      "catalog_id": "arxiv:2409.09354",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-09-14",
      "identifiers": {
        "arxiv": "2409.09354"
      },
      "record_updated_at": "2024-09-14"
    },
    "genre": "preprint",
    "id": "arxiv:2409.09354",
    "issued": {
      "date-parts": [
        [
          2024,
          9,
          14
        ]
      ]
    },
    "note": "First published: 2024-09-14; Recorded arXiv version: v1; Recorded version updated: 2024-09-14T07:54:25Z.",
    "title": "PeriGuru: A Peripheral Robotic Mobile App Operation Assistant based on GUI Image Understanding and Prompting with LLM",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2409.10811v4",
    "archive": "arXiv",
    "archive_location": "2409.10811",
    "author": [
      {
        "literal": "Shuqing Li"
      },
      {
        "literal": "Binchang Li"
      },
      {
        "literal": "Yepang Liu"
      },
      {
        "literal": "Cuiyun Gao"
      },
      {
        "literal": "Jianping Zhang"
      },
      {
        "literal": "Shing-Chi Cheung"
      },
      {
        "literal": "Michael R. Lyu"
      }
    ],
    "citation-key": "arxiv_2409_10811",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "2a32462e4cb09763750f8f22d7f4be32a6bdfe3db6c9b3de9c386dc7cd6b6f30",
        "submitted_at": "2024-09-17T00:58:00Z",
        "updated_at": "2025-10-01T17:58:44Z",
        "version": 4,
        "versioned_url": "https://arxiv.org/abs/2409.10811v4"
      },
      "canonical_source_url": "https://arxiv.org/abs/2409.10811",
      "catalog_id": "arxiv:2409.10811",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-09-17",
      "identifiers": {
        "arxiv": "2409.10811"
      },
      "record_updated_at": "2025-10-01"
    },
    "genre": "preprint",
    "id": "arxiv:2409.10811",
    "issued": {
      "date-parts": [
        [
          2024,
          9,
          17
        ]
      ]
    },
    "note": "First published: 2024-09-17; Recorded arXiv version: v4; Recorded version updated: 2025-10-01T17:58:44Z.",
    "title": "Grounded GUI Understanding for Vision-Based Spatial Intelligent Agent: Exemplified by Extended Reality Apps",
    "type": "article",
    "version": "4"
  },
  {
    "URL": "https://arxiv.org/abs/2409.12089v3",
    "archive": "arXiv",
    "archive_location": "2409.12089",
    "author": [
      {
        "literal": "Wayne Chi"
      },
      {
        "literal": "Ameet Talwalkar"
      },
      {
        "literal": "Chris Donahue"
      }
    ],
    "citation-key": "arxiv_2409_12089",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "a2f59976cec7adb9f9c88bd79bdfbeed040e4874b6d9ab0c229136f98101aa98",
        "submitted_at": "2024-09-18T16:04:10Z",
        "updated_at": "2024-10-06T21:25:34Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2409.12089v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2409.12089",
      "catalog_id": "arxiv:2409.12089",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-09-18",
      "identifiers": {
        "arxiv": "2409.12089"
      },
      "record_updated_at": "2024-10-06"
    },
    "genre": "preprint",
    "id": "arxiv:2409.12089",
    "issued": {
      "date-parts": [
        [
          2024,
          9,
          18
        ]
      ]
    },
    "note": "First published: 2024-09-18; Recorded arXiv version: v3; Recorded version updated: 2024-10-06T21:25:34Z.",
    "title": "The Impact of Element Ordering on LM Agent Performance",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2409.13711v2",
    "archive": "arXiv",
    "archive_location": "2409.13711",
    "author": [
      {
        "literal": "Maria Wang"
      },
      {
        "literal": "Srinivas Sunkara"
      },
      {
        "literal": "Gilles Baechler"
      },
      {
        "literal": "Jason Lin"
      },
      {
        "literal": "Yun Zhu"
      },
      {
        "literal": "Fedir Zubach"
      },
      {
        "literal": "Lei Shu"
      },
      {
        "literal": "Jindong Chen"
      }
    ],
    "citation-key": "arxiv_2409_13711",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "1ca44e6c98c09a2261b2cf8f3b6d18584b2d2471934b2dcac8d5b72c17b32e61",
        "submitted_at": "2024-09-06T18:44:25Z",
        "updated_at": "2024-09-24T18:38:02Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2409.13711v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2409.13711",
      "catalog_id": "arxiv:2409.13711",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-09-06",
      "identifiers": {
        "arxiv": "2409.13711"
      },
      "record_updated_at": "2024-09-24"
    },
    "genre": "preprint",
    "id": "arxiv:2409.13711",
    "issued": {
      "date-parts": [
        [
          2024,
          9,
          6
        ]
      ]
    },
    "note": "First published: 2024-09-06; Recorded arXiv version: v2; Recorded version updated: 2024-09-24T18:38:02Z.",
    "title": "WebQuest: A Benchmark for Multimodal QA on Web Page Sequences",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2409.14337v3",
    "archive": "arXiv",
    "archive_location": "2409.14337",
    "author": [
      {
        "literal": "Longxi Gao"
      },
      {
        "literal": "Li Zhang"
      },
      {
        "literal": "Shihe Wang"
      },
      {
        "literal": "Pengzhi Gao"
      },
      {
        "literal": "Wei Liu"
      },
      {
        "literal": "Jian Luan"
      },
      {
        "literal": "Shangguang Wang"
      },
      {
        "literal": "Yuanchun Li"
      },
      {
        "literal": "Mengwei Xu"
      }
    ],
    "citation-key": "arxiv_2409_14337",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "4bb00ad1be49c9bd51881827556b3a168d34c69a45e31053406f780ad2a62af1",
        "submitted_at": "2024-09-22T06:45:38Z",
        "updated_at": "2025-11-25T02:43:11Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2409.14337v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2409.14337",
      "catalog_id": "arxiv:2409.14337",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-09-22",
      "identifiers": {
        "arxiv": "2409.14337"
      },
      "record_updated_at": "2025-11-25"
    },
    "genre": "preprint",
    "id": "arxiv:2409.14337",
    "issued": {
      "date-parts": [
        [
          2024,
          9,
          22
        ]
      ]
    },
    "note": "First published: 2024-09-22; Recorded arXiv version: v3; Recorded version updated: 2025-11-25T02:43:11Z.",
    "title": "MobileViews: A Million-scale and Diverse Mobile GUI Dataset",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2409.14818v2",
    "archive": "arXiv",
    "archive_location": "2409.14818",
    "author": [
      {
        "literal": "Qinzhuo Wu"
      },
      {
        "literal": "Weikai Xu"
      },
      {
        "literal": "Wei Liu"
      },
      {
        "literal": "Tao Tan"
      },
      {
        "literal": "Jianfeng Liu"
      },
      {
        "literal": "Ang Li"
      },
      {
        "literal": "Jian Luan"
      },
      {
        "literal": "Bin Wang"
      },
      {
        "literal": "Shuo Shang"
      }
    ],
    "citation-key": "arxiv_2409_14818",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "cc22337ef29946dffcf7149df1008fd6cf02350c68d21ec0386e6485f5a14ebf",
        "submitted_at": "2024-09-23T08:47:54Z",
        "updated_at": "2024-10-03T05:23:22Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2409.14818v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2409.14818",
      "catalog_id": "arxiv:2409.14818",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "citation_edition": "record",
      "first_published_at": "2024-09-23",
      "identifiers": {
        "arxiv": "2409.14818"
      },
      "publication": {
        "authors": [
          "Qinzhuo Wu",
          "Weikai Xu",
          "Wei Liu",
          "Tao Tan",
          "Jianfeng Liu",
          "Ang Li",
          "Jian Luan",
          "Bin Wang",
          "Shuo Shang"
        ],
        "date_basis": "Explicit publisher citation_publication_date: 2024/11. Preserve supplied precision; do not substitute conference event dates.",
        "date_parts": [
          2024,
          11
        ],
        "doi": "10.18653/v1/2024.findings-emnlp.599",
        "event_dates": null,
        "evidence_urls": [
          "https://aclanthology.org/2024.findings-emnlp.599/",
          "https://aclanthology.org/2024.findings-emnlp.599.pdf"
        ],
        "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256. The publisher PDF title and complete first-page author list were visually checked.",
        "issue": null,
        "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot. Publisher spelling, initials, name annotations or author lists differ from the retained preprint. Authors follow the publisher PDF, page 1. The landing page and its BibTeX list the fifth author as Liujian Liujianfeng; the PDF names Jianfeng Liu.",
        "pages": "10231-10251",
        "pdf_url": "https://aclanthology.org/2024.findings-emnlp.599.pdf",
        "publisher": "Association for Computational Linguistics",
        "series": null,
        "title": "MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding",
        "type": "conference-paper",
        "url": "https://aclanthology.org/2024.findings-emnlp.599/",
        "venue": "Findings of the Association for Computational Linguistics: EMNLP 2024",
        "volume": null
      },
      "record_updated_at": "2024-10-03"
    },
    "genre": "preprint",
    "id": "arxiv:2409.14818",
    "issued": {
      "date-parts": [
        [
          2024,
          9,
          23
        ]
      ]
    },
    "note": "First published: 2024-09-23; Recorded arXiv version: v2; Recorded version updated: 2024-10-03T05:23:22Z.",
    "title": "MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2409.18060v2",
    "archive": "arXiv",
    "archive_location": "2409.18060",
    "author": [
      {
        "literal": "Sabrina Haque"
      },
      {
        "literal": "Christoph Csallner"
      }
    ],
    "citation-key": "arxiv_2409_18060",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "2d927b7644f0c6b3a49fbdf1aa976a00f2409adf9a72e1c04333438f66f1014b",
        "submitted_at": "2024-09-26T17:01:33Z",
        "updated_at": "2024-10-07T19:04:38Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2409.18060v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2409.18060",
      "catalog_id": "arxiv:2409.18060",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "adjacent",
      "first_published_at": "2024-09-26",
      "identifiers": {
        "arxiv": "2409.18060"
      },
      "record_updated_at": "2024-10-07"
    },
    "genre": "preprint",
    "id": "arxiv:2409.18060",
    "issued": {
      "date-parts": [
        [
          2024,
          9,
          26
        ]
      ]
    },
    "note": "First published: 2024-09-26; Recorded arXiv version: v2; Recorded version updated: 2024-10-07T19:04:38Z.",
    "title": "Inferring Alt-text For UI Icons With Large Language Models During App Development",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2410.00201v1",
    "archive": "arXiv",
    "archive_location": "2410.00201",
    "author": [
      {
        "literal": "Yi-Hao Peng"
      },
      {
        "literal": "Faria Huq"
      },
      {
        "literal": "Yue Jiang"
      },
      {
        "literal": "Jason Wu"
      },
      {
        "literal": "Amanda Xin Yue Li"
      },
      {
        "literal": "Jeffrey Bigham"
      },
      {
        "literal": "Amy Pavel"
      }
    ],
    "citation-key": "arxiv_2410_00201",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "a85dca895f00b442a60123c7c85cd26a90e3d1c2a810c91c32385f877bcd755a",
        "submitted_at": "2024-09-30T19:55:54Z",
        "updated_at": "2024-09-30T19:55:54Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2410.00201v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2410.00201",
      "catalog_id": "arxiv:2410.00201",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-09-30",
      "identifiers": {
        "arxiv": "2410.00201"
      },
      "record_updated_at": "2024-09-30"
    },
    "genre": "preprint",
    "id": "arxiv:2410.00201",
    "issued": {
      "date-parts": [
        [
          2024,
          9,
          30
        ]
      ]
    },
    "note": "First published: 2024-09-30; Recorded arXiv version: v1; Recorded version updated: 2024-09-30T19:55:54Z.",
    "title": "DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2410.13824v3",
    "archive": "arXiv",
    "archive_location": "2410.13824",
    "author": [
      {
        "literal": "Junpeng Liu"
      },
      {
        "literal": "Tianyue Ou"
      },
      {
        "literal": "Yifan Song"
      },
      {
        "literal": "Yuxiao Qu"
      },
      {
        "literal": "Wai Lam"
      },
      {
        "literal": "Chenyan Xiong"
      },
      {
        "literal": "Wenhu Chen"
      },
      {
        "literal": "Graham Neubig"
      },
      {
        "literal": "Xiang Yue"
      }
    ],
    "citation-key": "arxiv_2410_13824",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "2a3bcd26dff4f1d21a8a2772929c0c97cd1cc180a7606b0744e630dabae94609",
        "submitted_at": "2024-10-17T17:48:54Z",
        "updated_at": "2024-11-06T08:29:22Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2410.13824v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2410.13824",
      "catalog_id": "arxiv:2410.13824",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "citation_edition": "record",
      "first_published_at": "2024-10-17",
      "identifiers": {
        "arxiv": "2410.13824"
      },
      "publication": {
        "authors": [
          "Junpeng Liu",
          "Tianyue Ou",
          "Yifan Song",
          "Yuxiao Qu",
          "Wai Lam",
          "Chenyan Xiong",
          "Wenhu Chen",
          "Graham Neubig",
          "Xiang Yue"
        ],
        "date_basis": "Explicit publisher citation_publication_date: 2025-05-01. Preserve supplied precision; do not substitute conference event dates.",
        "date_parts": [
          2025,
          5,
          1
        ],
        "doi": null,
        "event_dates": null,
        "evidence_urls": [
          "https://proceedings.iclr.cc/paper_files/paper/2025/hash/2da53cd1abdae59150e35f4693834f32-Abstract-Conference.html"
        ],
        "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity.",
        "issue": null,
        "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.",
        "pages": "17971-18005",
        "pdf_url": "https://proceedings.iclr.cc/paper_files/paper/2025/file/2da53cd1abdae59150e35f4693834f32-Paper-Conference.pdf",
        "publisher": null,
        "series": null,
        "title": "Harnessing Webpage UIs for Text-Rich Visual Understanding",
        "type": "conference-paper",
        "url": "https://proceedings.iclr.cc/paper_files/paper/2025/hash/2da53cd1abdae59150e35f4693834f32-Abstract-Conference.html",
        "venue": "International Conference on Learning Representations",
        "volume": "2025"
      },
      "record_updated_at": "2024-11-06"
    },
    "genre": "preprint",
    "id": "arxiv:2410.13824",
    "issued": {
      "date-parts": [
        [
          2024,
          10,
          17
        ]
      ]
    },
    "note": "First published: 2024-10-17; Recorded arXiv version: v3; Recorded version updated: 2024-11-06T08:29:22Z.",
    "title": "Harnessing Webpage UIs for Text-Rich Visual Understanding",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2410.18967v2",
    "archive": "arXiv",
    "archive_location": "2410.18967",
    "author": [
      {
        "literal": "Zhangheng Li"
      },
      {
        "literal": "Keen You"
      },
      {
        "literal": "Haotian Zhang"
      },
      {
        "literal": "Di Feng"
      },
      {
        "literal": "Harsh Agrawal"
      },
      {
        "literal": "Xiujun Li"
      },
      {
        "literal": "Mohana Prasad Sathya Moorthy"
      },
      {
        "literal": "Jeff Nichols"
      },
      {
        "literal": "Yinfei Yang"
      },
      {
        "literal": "Zhe Gan"
      }
    ],
    "citation-key": "arxiv_2410_18967",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "299b7c631468e259ac9d25a1c4ebf507be57b7ee478c611d0a2597b588f6c4c8",
        "submitted_at": "2024-10-24T17:58:31Z",
        "updated_at": "2025-02-28T00:29:14Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2410.18967v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2410.18967",
      "catalog_id": "arxiv:2410.18967",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-10-24",
      "identifiers": {
        "arxiv": "2410.18967"
      },
      "record_updated_at": "2025-02-28"
    },
    "genre": "preprint",
    "id": "arxiv:2410.18967",
    "issued": {
      "date-parts": [
        [
          2024,
          10,
          24
        ]
      ]
    },
    "note": "First published: 2024-10-24; Recorded arXiv version: v2; Recorded version updated: 2025-02-28T00:29:14Z.",
    "title": "Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2410.19461v2",
    "archive": "arXiv",
    "archive_location": "2410.19461",
    "author": [
      {
        "literal": "Xuetian Chen"
      },
      {
        "literal": "Hangcheng Li"
      },
      {
        "literal": "Jiaqing Liang"
      },
      {
        "literal": "Sihang Jiang"
      },
      {
        "literal": "Deqing Yang"
      }
    ],
    "citation-key": "arxiv_2410_19461",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "dce2e22787c6e2cce95ecc4f5583bf94d7670b4b87ab75d2b8c7efb66fbcd1a8",
        "submitted_at": "2024-10-25T10:46:17Z",
        "updated_at": "2024-11-02T08:54:21Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2410.19461v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2410.19461",
      "catalog_id": "arxiv:2410.19461",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-10-25",
      "identifiers": {
        "arxiv": "2410.19461"
      },
      "record_updated_at": "2024-11-02"
    },
    "genre": "preprint",
    "id": "arxiv:2410.19461",
    "issued": {
      "date-parts": [
        [
          2024,
          10,
          25
        ]
      ]
    },
    "note": "First published: 2024-10-25; Recorded arXiv version: v2; Recorded version updated: 2024-11-02T08:54:21Z.",
    "title": "EDGE: Enhanced Grounded GUI Understanding with Enriched Multi-Granularity Synthetic Data",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2412.09362v1",
    "archive": "arXiv",
    "archive_location": "2412.09362",
    "author": [
      {
        "literal": "Huawen Shen"
      },
      {
        "literal": "Chang Liu"
      },
      {
        "literal": "Gengluo Li"
      },
      {
        "literal": "Xinlong Wang"
      },
      {
        "literal": "Yu Zhou"
      },
      {
        "literal": "Can Ma"
      },
      {
        "literal": "Xiangyang Ji"
      }
    ],
    "citation-key": "arxiv_2412_09362",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "ee5840bbd1404674f0e9509b305e995c4dece9257e3f2a79348dde9aee99928b",
        "submitted_at": "2024-12-12T15:29:36Z",
        "updated_at": "2024-12-12T15:29:36Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2412.09362v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2412.09362",
      "catalog_id": "arxiv:2412.09362",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-12-12",
      "identifiers": {
        "arxiv": "2412.09362"
      },
      "record_updated_at": "2024-12-12"
    },
    "genre": "preprint",
    "id": "arxiv:2412.09362",
    "issued": {
      "date-parts": [
        [
          2024,
          12,
          12
        ]
      ]
    },
    "note": "First published: 2024-12-12; Recorded arXiv version: v1; Recorded version updated: 2024-12-12T15:29:36Z.",
    "title": "Falcon-UI: Understanding GUI Before Following User Instructions",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2412.10342v2",
    "archive": "arXiv",
    "archive_location": "2412.10342",
    "author": [
      {
        "literal": "Zhiqi Ge"
      },
      {
        "literal": "Juncheng Li"
      },
      {
        "literal": "Xinglei Pang"
      },
      {
        "literal": "Minghe Gao"
      },
      {
        "literal": "Kaihang Pan"
      },
      {
        "literal": "Wang Lin"
      },
      {
        "literal": "Hao Fei"
      },
      {
        "literal": "Wenqiao Zhang"
      },
      {
        "literal": "Siliang Tang"
      },
      {
        "literal": "Yueting Zhuang"
      }
    ],
    "citation-key": "arxiv_2412_10342",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "6e7cab57b118ab76a9026e7ee800709f4e93969e19ad18f549f8b75ee657622b",
        "submitted_at": "2024-12-13T18:40:10Z",
        "updated_at": "2025-02-03T15:23:02Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2412.10342v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2412.10342",
      "catalog_id": "arxiv:2412.10342",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-12-13",
      "identifiers": {
        "arxiv": "2412.10342"
      },
      "record_updated_at": "2025-02-03"
    },
    "genre": "preprint",
    "id": "arxiv:2412.10342",
    "issued": {
      "date-parts": [
        [
          2024,
          12,
          13
        ]
      ]
    },
    "note": "First published: 2024-12-13; Recorded arXiv version: v2; Recorded version updated: 2025-02-03T15:23:02Z.",
    "title": "Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2502.08226v2",
    "archive": "arXiv",
    "archive_location": "2502.08226",
    "author": [
      {
        "literal": "Kunal Singh"
      },
      {
        "literal": "Shreyas Singh"
      },
      {
        "literal": "Mukund Khanna"
      }
    ],
    "citation-key": "arxiv_2502_08226",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "a60d581e4318db66495a0333b864757ec896576c720e40da4a881f8740b9d9cf",
        "submitted_at": "2025-02-12T09:12:30Z",
        "updated_at": "2025-02-14T06:23:57Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2502.08226v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2502.08226",
      "catalog_id": "arxiv:2502.08226",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-02-12",
      "identifiers": {
        "arxiv": "2502.08226"
      },
      "record_updated_at": "2025-02-14"
    },
    "genre": "preprint",
    "id": "arxiv:2502.08226",
    "issued": {
      "date-parts": [
        [
          2025,
          2,
          12
        ]
      ]
    },
    "note": "First published: 2025-02-12; Recorded arXiv version: v2; Recorded version updated: 2025-02-14T06:23:57Z.",
    "title": "TRISHUL: Towards Region Identification and Screen Hierarchy Understanding for Large VLM based GUI Agents",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2503.03196v2",
    "archive": "arXiv",
    "archive_location": "2503.03196",
    "author": [
      {
        "literal": "Zhiyuan Huang"
      },
      {
        "literal": "Ziming Cheng"
      },
      {
        "literal": "Junting Pan"
      },
      {
        "literal": "Zhaohui Hou"
      },
      {
        "literal": "Mingjie Zhan"
      }
    ],
    "citation-key": "arxiv_2503_03196",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "d45cacb33df18242eb3f47f6c89c56e41a146dd110e4b4dc5340062b9b981250",
        "submitted_at": "2025-03-05T05:30:22Z",
        "updated_at": "2025-04-16T15:34:51Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2503.03196v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2503.03196",
      "catalog_id": "arxiv:2503.03196",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-03-05",
      "identifiers": {
        "arxiv": "2503.03196"
      },
      "record_updated_at": "2025-04-16"
    },
    "genre": "preprint",
    "id": "arxiv:2503.03196",
    "issued": {
      "date-parts": [
        [
          2025,
          3,
          5
        ]
      ]
    },
    "note": "First published: 2025-03-05; Recorded arXiv version: v2; Recorded version updated: 2025-04-16T15:34:51Z.",
    "title": "SpiritSight Agent: Advanced GUI Agent with One Look",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2503.11170v1",
    "archive": "arXiv",
    "archive_location": "2503.11170",
    "author": [
      {
        "literal": "Yibin Xu"
      },
      {
        "literal": "Liang Yang"
      },
      {
        "literal": "Hao Chen"
      },
      {
        "literal": "Hua Wang"
      },
      {
        "literal": "Zhi Chen"
      },
      {
        "literal": "Yaohua Tang"
      }
    ],
    "citation-key": "arxiv_2503_11170",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "d2e6250e87ea9340914b457c4b0d471450f8cf49d2e2d53abd8e9e76105e908a",
        "submitted_at": "2025-03-14T08:16:02Z",
        "updated_at": "2025-03-14T08:16:02Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2503.11170v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2503.11170",
      "catalog_id": "arxiv:2503.11170",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-03-14",
      "identifiers": {
        "arxiv": "2503.11170"
      },
      "record_updated_at": "2025-03-14"
    },
    "genre": "preprint",
    "id": "arxiv:2503.11170",
    "issued": {
      "date-parts": [
        [
          2025,
          3,
          14
        ]
      ]
    },
    "note": "First published: 2025-03-14; Recorded arXiv version: v1; Recorded version updated: 2025-03-14T08:16:02Z.",
    "title": "DeskVision: Large Scale Desktop Region Captioning for Advanced GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2503.14021v1",
    "archive": "arXiv",
    "archive_location": "2503.14021",
    "author": [
      {
        "literal": "Ziwei Wang"
      },
      {
        "literal": "Weizhi Chen"
      },
      {
        "literal": "Leyang Yang"
      },
      {
        "literal": "Sheng Zhou"
      },
      {
        "literal": "Shengchu Zhao"
      },
      {
        "literal": "Hanbei Zhan"
      },
      {
        "literal": "Jiongchao Jin"
      },
      {
        "literal": "Liangcheng Li"
      },
      {
        "literal": "Zirui Shao"
      },
      {
        "literal": "Jiajun Bu"
      }
    ],
    "citation-key": "arxiv_2503_14021",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "b260fd1d7e28c8263710f116638e7aa7b51f46aac15199c8a29092161a13f37d",
        "submitted_at": "2025-03-18T08:32:22Z",
        "updated_at": "2025-03-18T08:32:22Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2503.14021v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2503.14021",
      "catalog_id": "arxiv:2503.14021",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-03-18",
      "identifiers": {
        "arxiv": "2503.14021"
      },
      "record_updated_at": "2025-03-18"
    },
    "genre": "preprint",
    "id": "arxiv:2503.14021",
    "issued": {
      "date-parts": [
        [
          2025,
          3,
          18
        ]
      ]
    },
    "note": "First published: 2025-03-18; Recorded arXiv version: v1; Recorded version updated: 2025-03-18T08:32:22Z.",
    "title": "MP-GUI: Modality Perception with MLLMs for GUI Understanding",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2503.15661v2",
    "archive": "arXiv",
    "archive_location": "2503.15661",
    "author": [
      {
        "literal": "Shravan Nayak"
      },
      {
        "literal": "Xiangru Jian"
      },
      {
        "literal": "Kevin Qinghong Lin"
      },
      {
        "literal": "Juan A. Rodriguez"
      },
      {
        "literal": "Montek Kalsi"
      },
      {
        "literal": "Rabiul Awal"
      },
      {
        "literal": "Nicolas Chapados"
      },
      {
        "literal": "M. Tamer Özsu"
      },
      {
        "literal": "Aishwarya Agrawal"
      },
      {
        "literal": "David Vazquez"
      },
      {
        "literal": "Christopher Pal"
      },
      {
        "literal": "Perouz Taslakian"
      },
      {
        "literal": "Spandana Gella"
      },
      {
        "literal": "Sai Rajeswar"
      }
    ],
    "citation-key": "arxiv_2503_15661",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "5abf3c7b08a4331d4f634d8cc63a7f8ff40713f7344231887dac1b5e061a8eae",
        "submitted_at": "2025-03-19T19:26:17Z",
        "updated_at": "2025-05-06T17:43:11Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2503.15661v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2503.15661",
      "catalog_id": "arxiv:2503.15661",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-03-19",
      "identifiers": {
        "arxiv": "2503.15661"
      },
      "record_updated_at": "2025-05-06"
    },
    "genre": "preprint",
    "id": "arxiv:2503.15661",
    "issued": {
      "date-parts": [
        [
          2025,
          3,
          19
        ]
      ]
    },
    "note": "First published: 2025-03-19; Recorded arXiv version: v2; Recorded version updated: 2025-05-06T17:43:11Z.",
    "title": "UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2503.20978v1",
    "archive": "arXiv",
    "archive_location": "2503.20978",
    "author": [
      {
        "literal": "Yiqiao Jin"
      },
      {
        "literal": "Stefano Petrangeli"
      },
      {
        "literal": "Yu Shen"
      },
      {
        "literal": "Gang Wu"
      }
    ],
    "citation-key": "arxiv_2503_20978",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "0888d0da1c5da9cf9956fd8b145a09f463aa432a60b142c4aea8d20b4aa84c4d",
        "submitted_at": "2025-03-26T20:41:24Z",
        "updated_at": "2025-03-26T20:41:24Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2503.20978v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2503.20978",
      "catalog_id": "arxiv:2503.20978",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-03-26",
      "identifiers": {
        "arxiv": "2503.20978"
      },
      "record_updated_at": "2025-03-26"
    },
    "genre": "preprint",
    "id": "arxiv:2503.20978",
    "issued": {
      "date-parts": [
        [
          2025,
          3,
          26
        ]
      ]
    },
    "note": "First published: 2025-03-26; Recorded arXiv version: v1; Recorded version updated: 2025-03-26T20:41:24Z.",
    "title": "ScreenLLM: Stateful Screen Schema for Efficient Action Understanding and Prediction",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2504.16419v2",
    "archive": "arXiv",
    "archive_location": "2504.16419",
    "author": [
      {
        "literal": "Qi Yang"
      },
      {
        "literal": "Weichen Bi"
      },
      {
        "literal": "Haiyang Shen"
      },
      {
        "literal": "Yaoqi Guo"
      },
      {
        "literal": "Yun Ma"
      }
    ],
    "citation-key": "arxiv_2504_16419",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "e1ec3311094166baac4de66ad0f083b66585c933f19cb66fc580bf128ad809ca",
        "submitted_at": "2025-04-23T05:01:25Z",
        "updated_at": "2025-04-27T06:52:23Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2504.16419v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2504.16419",
      "catalog_id": "arxiv:2504.16419",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-04-23",
      "identifiers": {
        "arxiv": "2504.16419"
      },
      "record_updated_at": "2025-04-27"
    },
    "genre": "preprint",
    "id": "arxiv:2504.16419",
    "issued": {
      "date-parts": [
        [
          2025,
          4,
          23
        ]
      ]
    },
    "note": "First published: 2025-04-23; Recorded arXiv version: v2; Recorded version updated: 2025-04-27T06:52:23Z.",
    "title": "PixelWeb: The First Web GUI Dataset with Pixel-Wise Labels",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2505.00684v2",
    "archive": "arXiv",
    "archive_location": "2505.00684",
    "author": [
      {
        "literal": "Tiange Luo"
      },
      {
        "literal": "Lajanugen Logeswaran"
      },
      {
        "literal": "Justin Johnson"
      },
      {
        "literal": "Honglak Lee"
      }
    ],
    "citation-key": "arxiv_2505_00684",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "3d2dc8ca397adce1ecf6cf53afa82a8d4f1825bf00277aeb117966f965abfe48",
        "submitted_at": "2025-05-01T17:45:59Z",
        "updated_at": "2025-07-14T17:45:50Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2505.00684v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2505.00684",
      "catalog_id": "arxiv:2505.00684",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-05-01",
      "identifiers": {
        "arxiv": "2505.00684"
      },
      "record_updated_at": "2025-07-14"
    },
    "genre": "preprint",
    "id": "arxiv:2505.00684",
    "issued": {
      "date-parts": [
        [
          2025,
          5,
          1
        ]
      ]
    },
    "note": "First published: 2025-05-01; Recorded arXiv version: v2; Recorded version updated: 2025-07-14T17:45:50Z.",
    "title": "Visual Test-time Scaling for GUI Agent Grounding",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2505.05026v5",
    "archive": "arXiv",
    "archive_location": "2505.05026",
    "author": [
      {
        "literal": "Jaehyun Jeon"
      },
      {
        "literal": "Min Soo Kim"
      },
      {
        "literal": "Jang Han Yoon"
      },
      {
        "literal": "Sumin Shim"
      },
      {
        "literal": "Yejin Choi"
      },
      {
        "literal": "Hanbin Kim"
      },
      {
        "literal": "Dae Hyun Kim"
      },
      {
        "literal": "Youngjae Yu"
      }
    ],
    "citation-key": "arxiv_2505_05026",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "3f65cd2856c554584baab9b1cbf9c5250b5c01d4f31980d69aefab727427ded2",
        "submitted_at": "2025-05-08T08:00:32Z",
        "updated_at": "2026-06-04T06:58:13Z",
        "version": 5,
        "versioned_url": "https://arxiv.org/abs/2505.05026v5"
      },
      "canonical_source_url": "https://arxiv.org/abs/2505.05026",
      "catalog_id": "arxiv:2505.05026",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "adjacent",
      "first_published_at": "2025-05-08",
      "identifiers": {
        "arxiv": "2505.05026"
      },
      "record_updated_at": "2026-06-04"
    },
    "genre": "preprint",
    "id": "arxiv:2505.05026",
    "issued": {
      "date-parts": [
        [
          2025,
          5,
          8
        ]
      ]
    },
    "note": "First published: 2025-05-08; Recorded arXiv version: v5; Recorded version updated: 2026-06-04T06:58:13Z.",
    "title": "Do MLLMs Capture How Interfaces Guide User Behavior? A Benchmark for Multimodal UI/UX Design Understanding",
    "type": "article",
    "version": "5"
  },
  {
    "URL": "https://arxiv.org/abs/2505.24878v1",
    "archive": "arXiv",
    "archive_location": "2505.24878",
    "author": [
      {
        "literal": "Yaxin Luo"
      },
      {
        "literal": "Zhaoyi Li"
      },
      {
        "literal": "Jiacheng Liu"
      },
      {
        "literal": "Jiacheng Cui"
      },
      {
        "literal": "Xiaohan Zhao"
      },
      {
        "literal": "Zhiqiang Shen"
      }
    ],
    "citation-key": "arxiv_2505_24878",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "3f2206333ca25b3f21df7ce49adfd8bc56521b9b8ace7a9b686eccf5b67276fa",
        "submitted_at": "2025-05-30T17:59:55Z",
        "updated_at": "2025-05-30T17:59:55Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2505.24878v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2505.24878",
      "catalog_id": "arxiv:2505.24878",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-05-30",
      "identifiers": {
        "arxiv": "2505.24878"
      },
      "record_updated_at": "2025-05-30"
    },
    "genre": "preprint",
    "id": "arxiv:2505.24878",
    "issued": {
      "date-parts": [
        [
          2025,
          5,
          30
        ]
      ]
    },
    "note": "First published: 2025-05-30; Recorded arXiv version: v1; Recorded version updated: 2025-05-30T17:59:55Z.",
    "title": "Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2507.00008v2",
    "archive": "arXiv",
    "archive_location": "2507.00008",
    "author": [
      {
        "literal": "Hang Wu"
      },
      {
        "literal": "Hongkai Chen"
      },
      {
        "literal": "Yujun Cai"
      },
      {
        "literal": "Chang Liu"
      },
      {
        "literal": "Qingwen Ye"
      },
      {
        "literal": "Ming-Hsuan Yang"
      },
      {
        "literal": "Yiwei Wang"
      }
    ],
    "citation-key": "arxiv_2507_00008",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "e423834b07e74155214597c0fbb66c26b949e2b726568a65617a670a9ab157fa",
        "submitted_at": "2025-06-12T03:13:21Z",
        "updated_at": "2025-09-05T17:21:02Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2507.00008v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2507.00008",
      "catalog_id": "arxiv:2507.00008",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-06-12",
      "identifiers": {
        "arxiv": "2507.00008"
      },
      "record_updated_at": "2025-09-05"
    },
    "genre": "preprint",
    "id": "arxiv:2507.00008",
    "issued": {
      "date-parts": [
        [
          2025,
          6,
          12
        ]
      ]
    },
    "note": "First published: 2025-06-12; Recorded arXiv version: v2; Recorded version updated: 2025-09-05T17:21:02Z.",
    "title": "DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2507.05673v1",
    "archive": "arXiv",
    "archive_location": "2507.05673",
    "author": [
      {
        "literal": "Joonhyung Park"
      },
      {
        "literal": "Peng Tang"
      },
      {
        "literal": "Sagnik Das"
      },
      {
        "literal": "Srikar Appalaraju"
      },
      {
        "literal": "Kunwar Yashraj Singh"
      },
      {
        "literal": "R. Manmatha"
      },
      {
        "literal": "Shabnam Ghadar"
      }
    ],
    "citation-key": "arxiv_2507_05673",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "aff9b208c446bd57f24258734557e0cd5caaf9146af68e594ec6a7e575919a6f",
        "submitted_at": "2025-07-08T04:56:57Z",
        "updated_at": "2025-07-08T04:56:57Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2507.05673v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2507.05673",
      "catalog_id": "arxiv:2507.05673",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-07-08",
      "identifiers": {
        "arxiv": "2507.05673"
      },
      "record_updated_at": "2025-07-08"
    },
    "genre": "preprint",
    "id": "arxiv:2507.05673",
    "issued": {
      "date-parts": [
        [
          2025,
          7,
          8
        ]
      ]
    },
    "note": "First published: 2025-07-08; Recorded arXiv version: v1; Recorded version updated: 2025-07-08T04:56:57Z.",
    "title": "R-VLM: Region-Aware Vision Language Model for Precise GUI Grounding",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2507.23779v1",
    "archive": "arXiv",
    "archive_location": "2507.23779",
    "author": [
      {
        "literal": "Miaosen Zhang"
      },
      {
        "literal": "Ziqiang Xu"
      },
      {
        "literal": "Jialiang Zhu"
      },
      {
        "literal": "Qi Dai"
      },
      {
        "literal": "Kai Qiu"
      },
      {
        "literal": "Yifan Yang"
      },
      {
        "literal": "Chong Luo"
      },
      {
        "literal": "Tianyi Chen"
      },
      {
        "literal": "Justin Wagle"
      },
      {
        "literal": "Tim Franklin"
      },
      {
        "literal": "Baining Guo"
      }
    ],
    "citation-key": "arxiv_2507_23779",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "2a7a32f30d2ada7f739e460429b6453d0e0e56364dda8653b0511ef2e9e6df2a",
        "submitted_at": "2025-07-31T17:59:09Z",
        "updated_at": "2025-07-31T17:59:09Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2507.23779v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2507.23779",
      "catalog_id": "arxiv:2507.23779",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-07-31",
      "identifiers": {
        "arxiv": "2507.23779"
      },
      "record_updated_at": "2025-07-31"
    },
    "genre": "preprint",
    "id": "arxiv:2507.23779",
    "issued": {
      "date-parts": [
        [
          2025,
          7,
          31
        ]
      ]
    },
    "note": "First published: 2025-07-31; Recorded arXiv version: v1; Recorded version updated: 2025-07-31T17:59:09Z.",
    "title": "Phi-Ground Tech Report: Advancing Perception in GUI Grounding",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2508.04025v1",
    "archive": "arXiv",
    "archive_location": "2508.04025",
    "author": [
      {
        "literal": "Chao Hao"
      },
      {
        "literal": "Shuai Wang"
      },
      {
        "literal": "Kaiwen Zhou"
      }
    ],
    "citation-key": "arxiv_2508_04025",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "499a462f9f14b8afdd367bb7cf7a7ffb1b2e166c212fb5c36686d3145f08ab5f",
        "submitted_at": "2025-08-06T02:38:02Z",
        "updated_at": "2025-08-06T02:38:02Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2508.04025v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2508.04025",
      "catalog_id": "arxiv:2508.04025",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-08-06",
      "identifiers": {
        "arxiv": "2508.04025"
      },
      "record_updated_at": "2025-08-06"
    },
    "genre": "preprint",
    "id": "arxiv:2508.04025",
    "issued": {
      "date-parts": [
        [
          2025,
          8,
          6
        ]
      ]
    },
    "note": "First published: 2025-08-06; Recorded arXiv version: v1; Recorded version updated: 2025-08-06T02:38:02Z.",
    "title": "Uncertainty-Aware GUI Agent: Adaptive Perception through Component Recommendation and Human-in-the-Loop Refinement",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2508.04412v4",
    "archive": "arXiv",
    "archive_location": "2508.04412",
    "author": [
      {
        "literal": "Thassilo M. Schiepanski"
      },
      {
        "literal": "Nicholas Piël"
      }
    ],
    "citation-key": "arxiv_2508_04412",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "789cfb56a83974c38e6f5e359dac5b6b3075cb70ac8afc178e36a901ce742041",
        "submitted_at": "2025-08-06T12:56:54Z",
        "updated_at": "2026-08-31T14:39:02Z",
        "version": 4,
        "versioned_url": "https://arxiv.org/abs/2508.04412v4"
      },
      "canonical_source_url": "https://arxiv.org/abs/2508.04412",
      "catalog_id": "arxiv:2508.04412",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-08-06",
      "identifiers": {
        "arxiv": "2508.04412"
      },
      "record_updated_at": "2026-08-31"
    },
    "genre": "preprint",
    "id": "arxiv:2508.04412",
    "issued": {
      "date-parts": [
        [
          2025,
          8,
          6
        ]
      ]
    },
    "note": "First published: 2025-08-06; Recorded arXiv version: v4; Recorded version updated: 2026-08-31T14:39:02Z.",
    "title": "Beyond Pixels: Exploring DOM Downsampling for LLM-Based Web Agents",
    "type": "article",
    "version": "4"
  },
  {
    "URL": "https://arxiv.org/abs/2508.09241v1",
    "archive": "arXiv",
    "archive_location": "2508.09241",
    "author": [
      {
        "literal": "Fengxian Ji"
      },
      {
        "literal": "Jingpu Yang"
      },
      {
        "literal": "Zirui Song"
      },
      {
        "literal": "Yuanxi Wang"
      },
      {
        "literal": "Zhexuan Cui"
      },
      {
        "literal": "Yuke Li"
      },
      {
        "literal": "Qian Jiang"
      },
      {
        "literal": "Miao Fang"
      },
      {
        "literal": "Xiuying Chen"
      }
    ],
    "citation-key": "arxiv_2508_09241",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "f8c91a1f85602760c706e56426c0d2d870bbc101ca500aa3c7c391938c3f1676",
        "submitted_at": "2025-08-12T15:12:42Z",
        "updated_at": "2025-08-12T15:12:42Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2508.09241v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2508.09241",
      "catalog_id": "arxiv:2508.09241",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-08-12",
      "identifiers": {
        "arxiv": "2508.09241"
      },
      "record_updated_at": "2025-08-12"
    },
    "genre": "preprint",
    "id": "arxiv:2508.09241",
    "issued": {
      "date-parts": [
        [
          2025,
          8,
          12
        ]
      ]
    },
    "note": "First published: 2025-08-12; Recorded arXiv version: v1; Recorded version updated: 2025-08-12T15:12:42Z.",
    "title": "FineState-Bench: A Comprehensive Benchmark for Fine-Grained State Control in GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2508.13634v3",
    "archive": "arXiv",
    "archive_location": "2508.13634",
    "author": [
      {
        "literal": "Jikai Chen"
      },
      {
        "literal": "Long Chen"
      },
      {
        "literal": "Dong Wang"
      },
      {
        "literal": "Qinglin Su"
      },
      {
        "literal": "Zhixuan Chu"
      },
      {
        "literal": "Bingguang Hao"
      },
      {
        "literal": "Leilei Gan"
      },
      {
        "literal": "Chenyi Zhuang"
      },
      {
        "literal": "Jinjie Gu"
      }
    ],
    "citation-key": "arxiv_2508_13634",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "dfb50e10184cded6c18d4c49401145bc7cfa00b0ba21bce964abe8f459af5626",
        "submitted_at": "2025-08-19T08:47:44Z",
        "updated_at": "2026-01-20T06:39:19Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2508.13634v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2508.13634",
      "catalog_id": "arxiv:2508.13634",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-08-19",
      "identifiers": {
        "arxiv": "2508.13634"
      },
      "record_updated_at": "2026-01-20"
    },
    "genre": "preprint",
    "id": "arxiv:2508.13634",
    "issued": {
      "date-parts": [
        [
          2025,
          8,
          19
        ]
      ]
    },
    "note": "First published: 2025-08-19; Recorded arXiv version: v3; Recorded version updated: 2026-01-20T06:39:19Z.",
    "title": "V2P: Visual Attention Calibration for GUI Grounding via Background Suppression and Center Peaking",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2509.04243v1",
    "archive": "arXiv",
    "archive_location": "2509.04243",
    "author": [
      {
        "literal": "Wanfu Wang"
      },
      {
        "literal": "Qipeng Huang"
      },
      {
        "literal": "Guangquan Xue"
      },
      {
        "literal": "Xiaobo Liang"
      },
      {
        "literal": "Juntao Li"
      }
    ],
    "citation-key": "arxiv_2509_04243",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "875e2452985bae9e67d7071121ab13f5205307ecc30bf33f237048a44e75b3bc",
        "submitted_at": "2025-09-04T14:17:01Z",
        "updated_at": "2025-09-04T14:17:01Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2509.04243v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2509.04243",
      "catalog_id": "arxiv:2509.04243",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-09-04",
      "identifiers": {
        "arxiv": "2509.04243"
      },
      "record_updated_at": "2025-09-04"
    },
    "genre": "preprint",
    "id": "arxiv:2509.04243",
    "issued": {
      "date-parts": [
        [
          2025,
          9,
          4
        ]
      ]
    },
    "note": "First published: 2025-09-04; Recorded arXiv version: v1; Recorded version updated: 2025-09-04T14:17:01Z.",
    "title": "Learning Active Perception via Self-Evolving Preference Optimization for GUI Grounding",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2509.04908v1",
    "archive": "arXiv",
    "archive_location": "2509.04908",
    "author": [
      {
        "literal": "Hongyi Jing"
      },
      {
        "literal": "Jiafu Chen"
      },
      {
        "literal": "Chen Rao"
      },
      {
        "literal": "Ziqiang Dang"
      },
      {
        "literal": "Jiajie Teng"
      },
      {
        "literal": "Tianyi Chu"
      },
      {
        "literal": "Juncheng Mo"
      },
      {
        "literal": "Shuo Fang"
      },
      {
        "literal": "Huaizhong Lin"
      },
      {
        "literal": "Rui Lv"
      },
      {
        "literal": "Chenguang Ma"
      },
      {
        "literal": "Lei Zhao"
      }
    ],
    "citation-key": "arxiv_2509_04908",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "f74081d31c98d18e10a5febc5de436a3788fc4156215e4be8fc54b1c53260f58",
        "submitted_at": "2025-09-05T08:24:12Z",
        "updated_at": "2025-09-05T08:24:12Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2509.04908v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2509.04908",
      "catalog_id": "arxiv:2509.04908",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-09-05",
      "identifiers": {
        "arxiv": "2509.04908"
      },
      "record_updated_at": "2025-09-05"
    },
    "genre": "preprint",
    "id": "arxiv:2509.04908",
    "issued": {
      "date-parts": [
        [
          2025,
          9,
          5
        ]
      ]
    },
    "note": "First published: 2025-09-05; Recorded arXiv version: v1; Recorded version updated: 2025-09-05T08:24:12Z.",
    "title": "SparkUI-Parser: Enhancing GUI Perception with Robust Grounding and Parsing",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2509.11548v2",
    "archive": "arXiv",
    "archive_location": "2509.11548",
    "author": [
      {
        "literal": "Weiming Li"
      },
      {
        "literal": "Yan Shao"
      },
      {
        "literal": "Jing Yang"
      },
      {
        "literal": "Yujing Lu"
      },
      {
        "literal": "Ling Zhong"
      },
      {
        "literal": "Yuhan Wang"
      },
      {
        "literal": "Min Yu"
      },
      {
        "literal": "Tongxiao Ruan"
      },
      {
        "literal": "Manni Duan"
      }
    ],
    "citation-key": "arxiv_2509_11548",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "75ffc21abebbc2c362798f3455b9e6240b58407572e5633d5171e5612cfae71b",
        "submitted_at": "2025-09-15T03:28:29Z",
        "updated_at": "2026-06-10T01:13:27Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2509.11548v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2509.11548",
      "catalog_id": "arxiv:2509.11548",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-09-15",
      "identifiers": {
        "arxiv": "2509.11548"
      },
      "record_updated_at": "2026-06-10"
    },
    "genre": "preprint",
    "id": "arxiv:2509.11548",
    "issued": {
      "date-parts": [
        [
          2025,
          9,
          15
        ]
      ]
    },
    "note": "First published: 2025-09-15; Recorded arXiv version: v2; Recorded version updated: 2026-06-10T01:13:27Z.",
    "title": "How Auxiliary Reasoning Unleashes GUI Grounding in VLMs",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2509.15532v1",
    "archive": "arXiv",
    "archive_location": "2509.15532",
    "author": [
      {
        "literal": "Xianhang Ye"
      },
      {
        "literal": "Yiqing Li"
      },
      {
        "literal": "Wei Dai"
      },
      {
        "literal": "Miancan Liu"
      },
      {
        "literal": "Ziyuan Chen"
      },
      {
        "literal": "Zhangye Han"
      },
      {
        "literal": "Hongbo Min"
      },
      {
        "literal": "Jinkui Ren"
      },
      {
        "literal": "Xiantao Zhang"
      },
      {
        "literal": "Wen Yang"
      },
      {
        "literal": "Zhi Jin"
      }
    ],
    "citation-key": "arxiv_2509_15532",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "e415074c6a4b4995350d6936d338682b9a4469f1cbed3a83e0ac44eee6f02bef",
        "submitted_at": "2025-09-19T02:34:50Z",
        "updated_at": "2025-09-19T02:34:50Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2509.15532v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2509.15532",
      "catalog_id": "arxiv:2509.15532",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-09-19",
      "identifiers": {
        "arxiv": "2509.15532"
      },
      "record_updated_at": "2025-09-19"
    },
    "genre": "preprint",
    "id": "arxiv:2509.15532",
    "issued": {
      "date-parts": [
        [
          2025,
          9,
          19
        ]
      ]
    },
    "note": "First published: 2025-09-19; Recorded arXiv version: v1; Recorded version updated: 2025-09-19T02:34:50Z.",
    "title": "GUI-ARP: Enhancing Grounding with Adaptive Region Perception for GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2509.21782v2",
    "archive": "arXiv",
    "archive_location": "2509.21782",
    "author": [
      {
        "literal": "Junliang Liu"
      },
      {
        "literal": "Jingyu Xiao"
      },
      {
        "literal": "Wenxin Tang"
      },
      {
        "literal": "Zhixian Wang"
      },
      {
        "literal": "Zipeng Xie"
      },
      {
        "literal": "Wenxuan Wang"
      },
      {
        "literal": "Minrui Zhang"
      },
      {
        "literal": "Shuanghe Yu"
      }
    ],
    "citation-key": "arxiv_2509_21782",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "8fed6f081e0330c54a304c79e8a4183865aae48f0e944545029d3de9852f8028",
        "submitted_at": "2025-09-26T02:38:14Z",
        "updated_at": "2026-03-04T16:31:39Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2509.21782v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2509.21782",
      "catalog_id": "arxiv:2509.21782",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-09-26",
      "identifiers": {
        "arxiv": "2509.21782"
      },
      "record_updated_at": "2026-03-04"
    },
    "genre": "preprint",
    "id": "arxiv:2509.21782",
    "issued": {
      "date-parts": [
        [
          2025,
          9,
          26
        ]
      ]
    },
    "note": "First published: 2025-09-26; Recorded arXiv version: v2; Recorded version updated: 2026-03-04T16:31:39Z.",
    "title": "Benchmarking MLLM-based Web Understanding: Reasoning, Robustness and Safety",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2509.23263v3",
    "archive": "arXiv",
    "archive_location": "2509.23263",
    "author": [
      {
        "literal": "Tao Xiong"
      },
      {
        "literal": "Xavier Hu"
      },
      {
        "literal": "Yurun Chen"
      },
      {
        "literal": "Yuhang Liu"
      },
      {
        "literal": "Changqiao Wu"
      },
      {
        "literal": "Pengzhi Gao"
      },
      {
        "literal": "Wei Liu"
      },
      {
        "literal": "Jian Luan"
      },
      {
        "literal": "Shengyu Zhang"
      }
    ],
    "citation-key": "arxiv_2509_23263",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "5b5375e77f087367383bb5de96cec46d8de6550d9a44bff6965b9201b6718a05",
        "submitted_at": "2025-09-27T11:42:36Z",
        "updated_at": "2026-08-30T18:12:14Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2509.23263v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2509.23263",
      "catalog_id": "arxiv:2509.23263",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-09-27",
      "identifiers": {
        "arxiv": "2509.23263"
      },
      "record_updated_at": "2026-08-30"
    },
    "genre": "preprint",
    "id": "arxiv:2509.23263",
    "issued": {
      "date-parts": [
        [
          2025,
          9,
          27
        ]
      ]
    },
    "note": "First published: 2025-09-27; Recorded arXiv version: v3; Recorded version updated: 2026-08-30T18:12:14Z.",
    "title": "GUI-PRA: Process Reward Agent for GUI Tasks",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2510.00536v2",
    "archive": "arXiv",
    "archive_location": "2510.00536",
    "author": [
      {
        "literal": "Kung-Hsiang Huang"
      },
      {
        "literal": "Haoyi Qiu"
      },
      {
        "literal": "Yutong Dai"
      },
      {
        "literal": "Caiming Xiong"
      },
      {
        "literal": "Chien-Sheng Wu"
      }
    ],
    "citation-key": "arxiv_2510_00536",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "e07a5a8f9c0aa39643bb919c2d637435669318420223d7d72b0ef3d733308852",
        "submitted_at": "2025-10-01T05:37:54Z",
        "updated_at": "2026-10-07T23:23:10Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2510.00536v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2510.00536",
      "catalog_id": "arxiv:2510.00536",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-10-01",
      "identifiers": {
        "arxiv": "2510.00536"
      },
      "record_updated_at": "2026-10-07"
    },
    "genre": "preprint",
    "id": "arxiv:2510.00536",
    "issued": {
      "date-parts": [
        [
          2025,
          10,
          1
        ]
      ]
    },
    "note": "First published: 2025-10-01; Recorded arXiv version: v2; Recorded version updated: 2026-10-07T23:23:10Z.",
    "title": "GUI-KV: Efficient GUI Agents via KV Cache with Spatio-Temporal Awareness",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2510.03230v1",
    "archive": "arXiv",
    "archive_location": "2510.03230",
    "author": [
      {
        "literal": "Suyuchen Wang"
      },
      {
        "literal": "Tianyu Zhang"
      },
      {
        "literal": "Ahmed Masry"
      },
      {
        "literal": "Christopher Pal"
      },
      {
        "literal": "Spandana Gella"
      },
      {
        "literal": "Bang Liu"
      },
      {
        "literal": "Perouz Taslakian"
      }
    ],
    "citation-key": "arxiv_2510_03230",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "7f0c7eedadb9a321b222d4081271d6c979a25e1f64714cea8cf2ff088c5e61df",
        "submitted_at": "2025-10-03T17:59:34Z",
        "updated_at": "2025-10-03T17:59:34Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2510.03230v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2510.03230",
      "catalog_id": "arxiv:2510.03230",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-10-03",
      "identifiers": {
        "arxiv": "2510.03230"
      },
      "record_updated_at": "2025-10-03"
    },
    "genre": "preprint",
    "id": "arxiv:2510.03230",
    "issued": {
      "date-parts": [
        [
          2025,
          10,
          3
        ]
      ]
    },
    "note": "First published: 2025-10-03; Recorded arXiv version: v1; Recorded version updated: 2025-10-03T17:59:34Z.",
    "title": "Improving GUI Grounding with Explicit Position-to-Coordinate Mapping",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2510.16051v2",
    "archive": "arXiv",
    "archive_location": "2510.16051",
    "author": [
      {
        "literal": "Sofiya Garkot"
      },
      {
        "literal": "Maksym Shamrai"
      },
      {
        "literal": "Ivan Synytsia"
      },
      {
        "literal": "Mariya Hirna"
      }
    ],
    "citation-key": "arxiv_2510_16051",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "6e4377fd6b510455afa1eb04c64e8e0b551e89d3b54ce31f241f283233985e1c",
        "submitted_at": "2025-10-16T19:03:45Z",
        "updated_at": "2026-03-24T14:39:38Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2510.16051v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2510.16051",
      "catalog_id": "arxiv:2510.16051",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-10-16",
      "identifiers": {
        "arxiv": "2510.16051"
      },
      "record_updated_at": "2026-03-24"
    },
    "genre": "preprint",
    "id": "arxiv:2510.16051",
    "issued": {
      "date-parts": [
        [
          2025,
          10,
          16
        ]
      ]
    },
    "note": "First published: 2025-10-16; Recorded arXiv version: v2; Recorded version updated: 2026-03-24T14:39:38Z.",
    "title": "GUIrilla: A Scalable Framework for Automated Desktop UI Exploration",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2511.00810v4",
    "archive": "arXiv",
    "archive_location": "2511.00810",
    "author": [
      {
        "literal": "Shijie Zhou"
      },
      {
        "literal": "Viet Dac Lai"
      },
      {
        "literal": "Hao Tan"
      },
      {
        "literal": "Jihyung Kil"
      },
      {
        "literal": "Wanrong Zhu"
      },
      {
        "literal": "Changyou Chen"
      },
      {
        "literal": "Ruiyi Zhang"
      }
    ],
    "citation-key": "arxiv_2511_00810",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "c2224c58c8fbac7a68f3757391f5e6a4f62c32fa42aae86bf9821c0755b402b1",
        "submitted_at": "2025-11-02T05:34:21Z",
        "updated_at": "2026-06-30T10:43:39Z",
        "version": 4,
        "versioned_url": "https://arxiv.org/abs/2511.00810v4"
      },
      "canonical_source_url": "https://arxiv.org/abs/2511.00810",
      "catalog_id": "arxiv:2511.00810",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-11-02",
      "identifiers": {
        "arxiv": "2511.00810"
      },
      "record_updated_at": "2026-06-30"
    },
    "genre": "preprint",
    "id": "arxiv:2511.00810",
    "issued": {
      "date-parts": [
        [
          2025,
          11,
          2
        ]
      ]
    },
    "note": "First published: 2025-11-02; Recorded arXiv version: v4; Recorded version updated: 2026-06-30T10:43:39Z.",
    "title": "GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding",
    "type": "article",
    "version": "4"
  },
  {
    "URL": "https://arxiv.org/abs/2511.13087v1",
    "archive": "arXiv",
    "archive_location": "2511.13087",
    "author": [
      {
        "literal": "SeokJoo Kwak"
      },
      {
        "literal": "Jihoon Kim"
      },
      {
        "literal": "Boyoun Kim"
      },
      {
        "literal": "Jung Jae Yoon"
      },
      {
        "literal": "Wooseok Jang"
      },
      {
        "literal": "Jeonghoon Hong"
      },
      {
        "literal": "Jaeho Yang"
      },
      {
        "literal": "Yeong-Dae Kwon"
      }
    ],
    "citation-key": "arxiv_2511_13087",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "2cdabdd4fc56b95c2b0c801fefd76d4c724aa0a1d7f762623d4314ca9a38e85c",
        "submitted_at": "2025-11-17T07:38:05Z",
        "updated_at": "2025-11-17T07:38:05Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2511.13087v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2511.13087",
      "catalog_id": "arxiv:2511.13087",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-11-17",
      "identifiers": {
        "arxiv": "2511.13087"
      },
      "record_updated_at": "2025-11-17"
    },
    "genre": "preprint",
    "id": "arxiv:2511.13087",
    "issued": {
      "date-parts": [
        [
          2025,
          11,
          17
        ]
      ]
    },
    "note": "First published: 2025-11-17; Recorded arXiv version: v1; Recorded version updated: 2025-11-17T07:38:05Z.",
    "title": "MEGA-GUI: Multi-stage Enhanced Grounding Agents for GUI Elements",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2511.21398v1",
    "archive": "arXiv",
    "archive_location": "2511.21398",
    "author": [
      {
        "literal": "Jiayuan Zhang"
      },
      {
        "literal": "Kaiquan Chen"
      },
      {
        "literal": "Zhihao Lu"
      },
      {
        "literal": "Enshen Zhou"
      },
      {
        "literal": "Qian Yu"
      },
      {
        "literal": "Jing Zhang"
      }
    ],
    "citation-key": "arxiv_2511_21398",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "af9da8a618674b5a40f95029c4797b48a850e0a99de827d3e526b21797f8eef4",
        "submitted_at": "2025-11-26T13:49:39Z",
        "updated_at": "2025-11-26T13:49:39Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2511.21398v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2511.21398",
      "catalog_id": "arxiv:2511.21398",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-11-26",
      "identifiers": {
        "arxiv": "2511.21398"
      },
      "record_updated_at": "2025-11-26"
    },
    "genre": "preprint",
    "id": "arxiv:2511.21398",
    "issued": {
      "date-parts": [
        [
          2025,
          11,
          26
        ]
      ]
    },
    "note": "First published: 2025-11-26; Recorded arXiv version: v1; Recorded version updated: 2025-11-26T13:49:39Z.",
    "title": "Prune4Web: DOM Tree Pruning Programming for Web Agent",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2512.00756v2",
    "archive": "arXiv",
    "archive_location": "2512.00756",
    "author": [
      {
        "literal": "Ruihan Chen"
      },
      {
        "literal": "Qiming Li"
      },
      {
        "literal": "Xiaocheng Feng"
      },
      {
        "literal": "Weihong Zhong"
      },
      {
        "literal": "Xiaoliang Yang"
      },
      {
        "literal": "Yuxuan Gu"
      },
      {
        "literal": "Zekun Zhou"
      },
      {
        "literal": "Yunfei Lu"
      },
      {
        "literal": "Haoyu Ren"
      },
      {
        "literal": "Kun Chen"
      },
      {
        "literal": "Dandan Tu"
      },
      {
        "literal": "Bing Qin"
      }
    ],
    "citation-key": "arxiv_2512_00756",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "bf16987178fc24fb483bfa82efecb1924c7528fd16ac94f1144fcc345748850f",
        "submitted_at": "2025-11-30T06:47:33Z",
        "updated_at": "2026-04-28T03:32:32Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2512.00756v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2512.00756",
      "catalog_id": "arxiv:2512.00756",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-11-30",
      "identifiers": {
        "arxiv": "2512.00756"
      },
      "record_updated_at": "2026-04-28"
    },
    "genre": "preprint",
    "id": "arxiv:2512.00756",
    "issued": {
      "date-parts": [
        [
          2025,
          11,
          30
        ]
      ]
    },
    "note": "First published: 2025-11-30; Recorded arXiv version: v2; Recorded version updated: 2026-04-28T03:32:32Z.",
    "title": "MPR-GUI: Benchmarking and Enhancing Multilingual Perception and Reasoning in GUI Agents",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2512.05941v1",
    "archive": "arXiv",
    "archive_location": "2512.05941",
    "author": [
      {
        "literal": "Zhiyuan Jiang"
      },
      {
        "literal": "Shenghao Xie"
      },
      {
        "literal": "Wenyi Li"
      },
      {
        "literal": "Wenqiang Zu"
      },
      {
        "literal": "Peihang Li"
      },
      {
        "literal": "Jiahao Qiu"
      },
      {
        "literal": "Siqi Pei"
      },
      {
        "literal": "Lei Ma"
      },
      {
        "literal": "Tiejun Huang"
      },
      {
        "literal": "Mengdi Wang"
      },
      {
        "literal": "Shilong Liu"
      }
    ],
    "citation-key": "arxiv_2512_05941",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "bac971bd0e7cd946f81e28d5976eb933cbb95b97ca846ee624a0c36b48760de7",
        "submitted_at": "2025-12-05T18:39:12Z",
        "updated_at": "2025-12-05T18:39:12Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2512.05941v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2512.05941",
      "catalog_id": "arxiv:2512.05941",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-12-05",
      "identifiers": {
        "arxiv": "2512.05941"
      },
      "record_updated_at": "2025-12-05"
    },
    "genre": "preprint",
    "id": "arxiv:2512.05941",
    "issued": {
      "date-parts": [
        [
          2025,
          12,
          5
        ]
      ]
    },
    "note": "First published: 2025-12-05; Recorded arXiv version: v1; Recorded version updated: 2025-12-05T18:39:12Z.",
    "title": "Zoom in, Click out: Unlocking and Evaluating the Potential of Zooming for GUI Grounding",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2512.17221v3",
    "archive": "arXiv",
    "archive_location": "2512.17221",
    "author": [
      {
        "literal": "Brandon Huang"
      },
      {
        "literal": "Hang Hua"
      },
      {
        "literal": "Zhuoran Yu"
      },
      {
        "literal": "Trevor Darrell"
      },
      {
        "literal": "Rogerio Feris"
      },
      {
        "literal": "Roei Herzig"
      }
    ],
    "citation-key": "arxiv_2512_17221",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "37cd0aa99ed8bad167e25f6e2b48e7cd1cf01249508555f657215213ee94a301",
        "submitted_at": "2025-12-19T04:09:24Z",
        "updated_at": "2025-12-31T17:30:11Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2512.17221v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2512.17221",
      "catalog_id": "arxiv:2512.17221",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-12-19",
      "identifiers": {
        "arxiv": "2512.17221"
      },
      "record_updated_at": "2025-12-31"
    },
    "genre": "preprint",
    "id": "arxiv:2512.17221",
    "issued": {
      "date-parts": [
        [
          2025,
          12,
          19
        ]
      ]
    },
    "note": "First published: 2025-12-19; Recorded arXiv version: v3; Recorded version updated: 2025-12-31T17:30:11Z.",
    "title": "DAVE: A VLM Vision Encoder for Document Understanding and Web Agents",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2512.22009v1",
    "archive": "arXiv",
    "archive_location": "2512.22009",
    "author": [
      {
        "literal": "Sarthak Mehrotra"
      },
      {
        "literal": "Sairam V C Rebbapragada"
      },
      {
        "literal": "Mani Hemanth Reddy Bonthu"
      },
      {
        "literal": "Vineeth N Balasubramanian"
      }
    ],
    "citation-key": "arxiv_2512_22009",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "041466768673c1ea49bceda2ad08784c0fa0e896bcee5452a1e41d51ac3b81d8",
        "submitted_at": "2025-12-26T12:09:15Z",
        "updated_at": "2025-12-26T12:09:15Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2512.22009v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2512.22009",
      "catalog_id": "arxiv:2512.22009",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-12-26",
      "identifiers": {
        "arxiv": "2512.22009"
      },
      "record_updated_at": "2025-12-26"
    },
    "genre": "preprint",
    "id": "arxiv:2512.22009",
    "issued": {
      "date-parts": [
        [
          2025,
          12,
          26
        ]
      ]
    },
    "note": "First published: 2025-12-26; Recorded arXiv version: v1; Recorded version updated: 2025-12-26T12:09:15Z.",
    "title": "iSHIFT: Lightweight Slow-Fast GUI Agent with Adaptive Perception",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2601.03928v1",
    "archive": "arXiv",
    "archive_location": "2601.03928",
    "author": [
      {
        "literal": "Mingyu Ouyang"
      },
      {
        "literal": "Kevin Qinghong Lin"
      },
      {
        "literal": "Mike Zheng Shou"
      },
      {
        "literal": "Hwee Tou Ng"
      }
    ],
    "citation-key": "arxiv_2601_03928",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "518a9699a6c11e6f61b655f4016170c50bf5d949e477134521df1c0214320046",
        "submitted_at": "2026-01-07T13:48:12Z",
        "updated_at": "2026-01-07T13:48:12Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2601.03928v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2601.03928",
      "catalog_id": "arxiv:2601.03928",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-01-07",
      "identifiers": {
        "arxiv": "2601.03928"
      },
      "record_updated_at": "2026-01-07"
    },
    "genre": "preprint",
    "id": "arxiv:2601.03928",
    "issued": {
      "date-parts": [
        [
          2026,
          1,
          7
        ]
      ]
    },
    "note": "First published: 2026-01-07; Recorded arXiv version: v1; Recorded version updated: 2026-01-07T13:48:12Z.",
    "title": "FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2601.09770v1",
    "archive": "arXiv",
    "archive_location": "2601.09770",
    "author": [
      {
        "literal": "Chen Chen"
      },
      {
        "literal": "Jiawei Shao"
      },
      {
        "literal": "Dakuan Lu"
      },
      {
        "literal": "Haoyi Hu"
      },
      {
        "literal": "Xiangcheng Liu"
      },
      {
        "literal": "Hantao Yao"
      },
      {
        "literal": "Wu Liu"
      }
    ],
    "citation-key": "arxiv_2601_09770",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "0d5ed7e72534fc55d028d4f25cb98b2373c88b622cf76396933d7a49d8ecf2e8",
        "submitted_at": "2026-01-14T14:27:28Z",
        "updated_at": "2026-01-14T14:27:28Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2601.09770v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2601.09770",
      "catalog_id": "arxiv:2601.09770",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-01-14",
      "identifiers": {
        "arxiv": "2601.09770"
      },
      "record_updated_at": "2026-01-14"
    },
    "genre": "preprint",
    "id": "arxiv:2601.09770",
    "issued": {
      "date-parts": [
        [
          2026,
          1,
          14
        ]
      ]
    },
    "note": "First published: 2026-01-14; Recorded arXiv version: v1; Recorded version updated: 2026-01-14T14:27:28Z.",
    "title": "GUI-Eyes: Tool-Augmented Perception for Visual Grounding in GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2602.01576v2",
    "archive": "arXiv",
    "archive_location": "2602.01576",
    "author": [
      {
        "literal": "Woosung Koh"
      },
      {
        "literal": "Sungjun Han"
      },
      {
        "literal": "Segyu Lee"
      },
      {
        "literal": "Se-Young Yun"
      },
      {
        "literal": "Jamin Shin"
      }
    ],
    "citation-key": "arxiv_2602_01576",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "7c29d1404b02c4f5ef2cdaf78bdb0f9062b1b85ec1a154408bc8f49446c28d08",
        "submitted_at": "2026-02-02T03:12:16Z",
        "updated_at": "2026-05-23T02:41:44Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2602.01576v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2602.01576",
      "catalog_id": "arxiv:2602.01576",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-02-02",
      "identifiers": {
        "arxiv": "2602.01576"
      },
      "record_updated_at": "2026-05-23"
    },
    "genre": "preprint",
    "id": "arxiv:2602.01576",
    "issued": {
      "date-parts": [
        [
          2026,
          2,
          2
        ]
      ]
    },
    "note": "First published: 2026-02-02; Recorded arXiv version: v2; Recorded version updated: 2026-05-23T02:41:44Z.",
    "title": "Generative Visual Code Mobile World Models",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2602.06351v1",
    "archive": "arXiv",
    "archive_location": "2602.06351",
    "author": [
      {
        "literal": "Longhui Ma"
      },
      {
        "literal": "Di Zhao"
      },
      {
        "literal": "Siwei Wang"
      },
      {
        "literal": "Zhao Lv"
      },
      {
        "literal": "Miao Wang"
      }
    ],
    "citation-key": "arxiv_2602_06351",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "2591e0dab6a84b5db2631ddc94a2c0b65b13a97d06d411ab6ad4e243fe3d3e1e",
        "submitted_at": "2026-02-06T03:27:55Z",
        "updated_at": "2026-02-06T03:27:55Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2602.06351v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2602.06351",
      "catalog_id": "arxiv:2602.06351",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-02-06",
      "identifiers": {
        "arxiv": "2602.06351"
      },
      "record_updated_at": "2026-02-06"
    },
    "genre": "preprint",
    "id": "arxiv:2602.06351",
    "issued": {
      "date-parts": [
        [
          2026,
          2,
          6
        ]
      ]
    },
    "note": "First published: 2026-02-06; Recorded arXiv version: v1; Recorded version updated: 2026-02-06T03:27:55Z.",
    "title": "Trifuse: Enhancing Attention-Based GUI Grounding via Multimodal Fusion",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2602.09007v3",
    "archive": "arXiv",
    "archive_location": "2602.09007",
    "author": [
      {
        "literal": "Haodong Li"
      },
      {
        "literal": "Jingwei Wu"
      },
      {
        "literal": "Quan Sun"
      },
      {
        "literal": "Guopeng Li"
      },
      {
        "literal": "Juanxi Tian"
      },
      {
        "literal": "Ziyu Guo"
      },
      {
        "literal": "Donghao Zhou"
      },
      {
        "literal": "Tianfei Ren"
      },
      {
        "literal": "Huanyu Zhang"
      },
      {
        "literal": "Yanlin Lai"
      },
      {
        "literal": "Ruichuan An"
      },
      {
        "literal": "Hongbo Peng"
      },
      {
        "literal": "Yuhong Dai"
      },
      {
        "literal": "Jia Wang"
      },
      {
        "literal": "Ziyang Meng"
      },
      {
        "literal": "Zheng Ge"
      },
      {
        "literal": "Xiangyu Zhang"
      },
      {
        "literal": "Daxin Jiang"
      },
      {
        "literal": "Pheng-Ann Heng"
      }
    ],
    "citation-key": "arxiv_2602_09007",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "43a01e0eb848a57a84767836d2c3c982bbf6094d22a3e70652dd42af52760bc5",
        "submitted_at": "2026-02-09T18:52:02Z",
        "updated_at": "2026-09-26T18:28:57Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2602.09007v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2602.09007",
      "catalog_id": "arxiv:2602.09007",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-02-09",
      "identifiers": {
        "arxiv": "2602.09007"
      },
      "record_updated_at": "2026-09-26"
    },
    "genre": "preprint",
    "id": "arxiv:2602.09007",
    "issued": {
      "date-parts": [
        [
          2026,
          2,
          9
        ]
      ]
    },
    "note": "First published: 2026-02-09; Recorded arXiv version: v3; Recorded version updated: 2026-09-26T18:28:57Z.",
    "title": "GUI-GenBench: Evaluating Image Generation Models as Interactive GUI Environments",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2602.10139v3",
    "archive": "arXiv",
    "archive_location": "2602.10139",
    "author": [
      {
        "literal": "Lepeng Zhao"
      },
      {
        "literal": "Zhenhua Zou"
      },
      {
        "literal": "Shuo Li"
      },
      {
        "literal": "Zhuotao Liu"
      }
    ],
    "citation-key": "arxiv_2602_10139",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "727279bf83a67f66fa8f173d028936fe0bdae63e9f23800d98476da10201ad0d",
        "submitted_at": "2026-02-08T15:50:04Z",
        "updated_at": "2026-04-26T01:34:23Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2602.10139v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2602.10139",
      "catalog_id": "arxiv:2602.10139",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-02-08",
      "identifiers": {
        "arxiv": "2602.10139"
      },
      "record_updated_at": "2026-04-26"
    },
    "genre": "preprint",
    "id": "arxiv:2602.10139",
    "issued": {
      "date-parts": [
        [
          2026,
          2,
          8
        ]
      ]
    },
    "note": "First published: 2026-02-08; Recorded arXiv version: v3; Recorded version updated: 2026-04-26T01:34:23Z.",
    "title": "Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2602.14276v2",
    "archive": "arXiv",
    "archive_location": "2602.14276",
    "author": [
      {
        "literal": "A. Said Gurbuz"
      },
      {
        "literal": "Sunghwan Hong"
      },
      {
        "literal": "Ahmed Nassar"
      },
      {
        "literal": "Marc Pollefeys"
      },
      {
        "literal": "Peter Staar"
      }
    ],
    "citation-key": "arxiv_2602_14276",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "d7c6e23f704562c4ae4db9e0b4f8f2a8dde1318efc08876ee57f5967b178257e",
        "submitted_at": "2026-02-15T19:00:02Z",
        "updated_at": "2026-05-01T17:32:06Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2602.14276v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2602.14276",
      "catalog_id": "arxiv:2602.14276",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-02-15",
      "identifiers": {
        "arxiv": "2602.14276"
      },
      "record_updated_at": "2026-05-01"
    },
    "genre": "preprint",
    "id": "arxiv:2602.14276",
    "issued": {
      "date-parts": [
        [
          2026,
          2,
          15
        ]
      ]
    },
    "note": "First published: 2026-02-15; Recorded arXiv version: v2; Recorded version updated: 2026-05-01T17:32:06Z.",
    "title": "ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2603.08013v1",
    "archive": "arXiv",
    "archive_location": "2603.08013",
    "author": [
      {
        "literal": "Yuxiang Chai"
      },
      {
        "literal": "Shunye Tang"
      },
      {
        "literal": "Han Xiao"
      },
      {
        "literal": "Rui Liu"
      },
      {
        "literal": "Hongsheng Li"
      }
    ],
    "citation-key": "arxiv_2603_08013",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "7334e01b1fbf5cdd02c275c73d2a1b5c2931718d6019fcf6a0ea72b449704d94",
        "submitted_at": "2026-03-09T06:41:32Z",
        "updated_at": "2026-03-09T06:41:32Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2603.08013v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2603.08013",
      "catalog_id": "arxiv:2603.08013",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-03-09",
      "identifiers": {
        "arxiv": "2603.08013"
      },
      "record_updated_at": "2026-03-09"
    },
    "genre": "preprint",
    "id": "arxiv:2603.08013",
    "issued": {
      "date-parts": [
        [
          2026,
          3,
          9
        ]
      ]
    },
    "note": "First published: 2026-03-09; Recorded arXiv version: v1; Recorded version updated: 2026-03-09T06:41:32Z.",
    "title": "PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2603.14448v1",
    "archive": "arXiv",
    "archive_location": "2603.14448",
    "author": [
      {
        "literal": "Ziwei Liu"
      },
      {
        "literal": "Tao Feng"
      },
      {
        "literal": "Borui Kang"
      },
      {
        "literal": "Yanbing Yang"
      },
      {
        "literal": "Jun Luo"
      }
    ],
    "citation-key": "arxiv_2603_14448",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "b4507a652e2b3c3857289763442fffd8db21726b97fb7b6304ad61a2139ef5af",
        "submitted_at": "2026-03-15T15:47:47Z",
        "updated_at": "2026-03-15T15:47:47Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2603.14448v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2603.14448",
      "catalog_id": "arxiv:2603.14448",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-03-15",
      "identifiers": {
        "arxiv": "2603.14448"
      },
      "record_updated_at": "2026-03-15"
    },
    "genre": "preprint",
    "id": "arxiv:2603.14448",
    "issued": {
      "date-parts": [
        [
          2026,
          3,
          15
        ]
      ]
    },
    "note": "First published: 2026-03-15; Recorded arXiv version: v1; Recorded version updated: 2026-03-15T15:47:47Z.",
    "title": "Zoom to Essence: Trainless GUI Grounding by Inferring upon Interface Elements",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2603.15039v1",
    "archive": "arXiv",
    "archive_location": "2603.15039",
    "author": [
      {
        "literal": "Yang Li"
      },
      {
        "literal": "Yuchen Liu"
      },
      {
        "literal": "Haoyu Lu"
      },
      {
        "literal": "Zhiqiang Xia"
      },
      {
        "literal": "Hongzhen Wang"
      },
      {
        "literal": "Kaiyang Han"
      },
      {
        "literal": "Changpeng Yang"
      },
      {
        "literal": "Jinyang Wu"
      },
      {
        "literal": "Jiaming Xu"
      },
      {
        "literal": "Runyu Shi"
      },
      {
        "literal": "Ying Huang"
      }
    ],
    "citation-key": "arxiv_2603_15039",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "bf6c3df80e405968d9ae2353639f3e039d3fcf8351d89db212bda038e3dfac9b",
        "submitted_at": "2026-03-16T09:45:33Z",
        "updated_at": "2026-03-16T09:45:33Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2603.15039v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2603.15039",
      "catalog_id": "arxiv:2603.15039",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-03-16",
      "identifiers": {
        "arxiv": "2603.15039"
      },
      "record_updated_at": "2026-03-16"
    },
    "genre": "preprint",
    "id": "arxiv:2603.15039",
    "issued": {
      "date-parts": [
        [
          2026,
          3,
          16
        ]
      ]
    },
    "note": "First published: 2026-03-16; Recorded arXiv version: v1; Recorded version updated: 2026-03-16T09:45:33Z.",
    "title": "GUI-CEval: A Hierarchical and Comprehensive Chinese Benchmark for Mobile GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2603.17357v1",
    "archive": "arXiv",
    "archive_location": "2603.17357",
    "author": [
      {
        "literal": "Nathan Zhao"
      }
    ],
    "citation-key": "arxiv_2603_17357",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "e3b429d277ec776af18977a72aaeb95000a4fedf66aa89c0366ab02120d4cdbe",
        "submitted_at": "2026-03-18T04:41:16Z",
        "updated_at": "2026-03-18T04:41:16Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2603.17357v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2603.17357",
      "catalog_id": "arxiv:2603.17357",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-03-18",
      "identifiers": {
        "arxiv": "2603.17357"
      },
      "record_updated_at": "2026-03-18"
    },
    "genre": "preprint",
    "id": "arxiv:2603.17357",
    "issued": {
      "date-parts": [
        [
          2026,
          3,
          18
        ]
      ]
    },
    "note": "First published: 2026-03-18; Recorded arXiv version: v1; Recorded version updated: 2026-03-18T04:41:16Z.",
    "title": "WebPII: Benchmarking Visual PII Detection for Computer-Use Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2603.17441v1",
    "archive": "arXiv",
    "archive_location": "2603.17441",
    "author": [
      {
        "literal": "Siqi Pei"
      },
      {
        "literal": "Liang Tang"
      },
      {
        "literal": "Tiaonan Duan"
      },
      {
        "literal": "Long Chen"
      },
      {
        "literal": "Shuxian Li"
      },
      {
        "literal": "Kaer Huang"
      },
      {
        "literal": "Yanzhe Jing"
      },
      {
        "literal": "Yiqiang Yan"
      },
      {
        "literal": "Bo Zhang"
      },
      {
        "literal": "Chenghao Jiang"
      },
      {
        "literal": "Borui Zhang"
      },
      {
        "literal": "Jiwen Lu"
      }
    ],
    "citation-key": "arxiv_2603_17441",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "2101a32746d6c668bff79461983b2e12138959f49ab3cfcb542ecbd629317f1d",
        "submitted_at": "2026-03-18T07:26:18Z",
        "updated_at": "2026-03-18T07:26:18Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2603.17441v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2603.17441",
      "catalog_id": "arxiv:2603.17441",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-03-18",
      "identifiers": {
        "arxiv": "2603.17441"
      },
      "record_updated_at": "2026-03-18"
    },
    "genre": "preprint",
    "id": "arxiv:2603.17441",
    "issued": {
      "date-parts": [
        [
          2026,
          3,
          18
        ]
      ]
    },
    "note": "First published: 2026-03-18; Recorded arXiv version: v1; Recorded version updated: 2026-03-18T07:26:18Z.",
    "title": "AdaZoom-GUI: Adaptive Zoom-based GUI Grounding with Instruction Refinement",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2603.20351v1",
    "archive": "arXiv",
    "archive_location": "2603.20351",
    "author": [
      {
        "literal": "Yizhe Zhao"
      },
      {
        "literal": "Yongjian Fu"
      },
      {
        "literal": "Zihao Feng"
      },
      {
        "literal": "Hao Pan"
      },
      {
        "literal": "Yongheng Deng"
      },
      {
        "literal": "Yaoxue Zhang"
      },
      {
        "literal": "Ju Ren"
      }
    ],
    "citation-key": "arxiv_2603_20351",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "f25f4999fc9d20433f96e22651311cccf78b5e2ad7cbc5578fe1765ac8be6a00",
        "submitted_at": "2026-03-20T12:19:41Z",
        "updated_at": "2026-03-20T12:19:41Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2603.20351v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2603.20351",
      "catalog_id": "arxiv:2603.20351",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-03-20",
      "identifiers": {
        "arxiv": "2603.20351"
      },
      "record_updated_at": "2026-03-20"
    },
    "genre": "preprint",
    "id": "arxiv:2603.20351",
    "issued": {
      "date-parts": [
        [
          2026,
          3,
          20
        ]
      ]
    },
    "note": "First published: 2026-03-20; Recorded arXiv version: v1; Recorded version updated: 2026-03-20T12:19:41Z.",
    "title": "MANA: Towards Efficient Mobile Ad Detection via Multimodal Agentic UI Navigation",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2603.25864v1",
    "archive": "arXiv",
    "archive_location": "2603.25864",
    "author": [
      {
        "literal": "Saelyne Yang"
      },
      {
        "literal": "Jaesang Yu"
      },
      {
        "literal": "Yi-Hao Peng"
      },
      {
        "literal": "Kevin Qinghong Lin"
      },
      {
        "literal": "Jae Won Cho"
      },
      {
        "literal": "Yale Song"
      },
      {
        "literal": "Juho Kim"
      }
    ],
    "citation-key": "arxiv_2603_25864",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "9b3dd3efca196fa3dd168431102dbb5f0f763e7d9e54b3d709ad2362a9c6f154",
        "submitted_at": "2026-03-26T19:37:53Z",
        "updated_at": "2026-03-26T19:37:53Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2603.25864v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2603.25864",
      "catalog_id": "arxiv:2603.25864",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-03-26",
      "identifiers": {
        "arxiv": "2603.25864"
      },
      "record_updated_at": "2026-03-26"
    },
    "genre": "preprint",
    "id": "arxiv:2603.25864",
    "issued": {
      "date-parts": [
        [
          2026,
          3,
          26
        ]
      ]
    },
    "note": "First published: 2026-03-26; Recorded arXiv version: v1; Recorded version updated: 2026-03-26T19:37:53Z.",
    "title": "GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Tasks",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2603.26041v4",
    "archive": "arXiv",
    "archive_location": "2603.26041",
    "author": [
      {
        "literal": "Daiqiang Li"
      },
      {
        "literal": "Zihao Pan"
      },
      {
        "literal": "Zeyu Zhang"
      },
      {
        "literal": "Xuyang Liu"
      },
      {
        "literal": "Shijia Xu"
      },
      {
        "literal": "Ronghao Chen"
      },
      {
        "literal": "Huacan Wang"
      },
      {
        "literal": "Honggang Chen"
      },
      {
        "literal": "Linfeng Zhang"
      },
      {
        "literal": "Zhangquan Chen"
      },
      {
        "literal": "Haiyun Jiang"
      }
    ],
    "citation-key": "arxiv_2603_26041",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "738d5048bb7a137d848b6f6068a7ce92694469f1e7bce0702dce422c230a3d0b",
        "submitted_at": "2026-03-27T03:21:19Z",
        "updated_at": "2026-08-09T16:37:37Z",
        "version": 4,
        "versioned_url": "https://arxiv.org/abs/2603.26041v4"
      },
      "canonical_source_url": "https://arxiv.org/abs/2603.26041",
      "catalog_id": "arxiv:2603.26041",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-03-27",
      "identifiers": {
        "arxiv": "2603.26041"
      },
      "record_updated_at": "2026-08-09"
    },
    "genre": "preprint",
    "id": "arxiv:2603.26041",
    "issued": {
      "date-parts": [
        [
          2026,
          3,
          27
        ]
      ]
    },
    "note": "First published: 2026-03-27; Recorded arXiv version: v4; Recorded version updated: 2026-08-09T16:37:37Z.",
    "title": "Where and How to Prune: An Empirical Study of Visual Token Pruning for GUI Agent Navigation",
    "type": "article",
    "version": "4"
  },
  {
    "URL": "https://arxiv.org/abs/2603.28069v1",
    "archive": "arXiv",
    "archive_location": "2603.28069",
    "author": [
      {
        "literal": "Christopher Clark"
      },
      {
        "literal": "Yue Yang"
      },
      {
        "literal": "Jae Sung Park"
      },
      {
        "literal": "Zixian Ma"
      },
      {
        "literal": "Jieyu Zhang"
      },
      {
        "literal": "Rohun Tripathi"
      },
      {
        "literal": "Mohammadreza Salehi"
      },
      {
        "literal": "Sangho Lee"
      },
      {
        "literal": "Taira Anderson"
      },
      {
        "literal": "Winson Han"
      },
      {
        "literal": "Ranjay Krishna"
      }
    ],
    "citation-key": "arxiv_2603_28069",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "7fe857c9f7e7819a9c2f99448f77bbeae15ae4e2ac8ad308000f3d217b0177fc",
        "submitted_at": "2026-03-30T06:15:06Z",
        "updated_at": "2026-03-30T06:15:06Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2603.28069v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2603.28069",
      "catalog_id": "arxiv:2603.28069",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "adjacent",
      "first_published_at": "2026-03-30",
      "identifiers": {
        "arxiv": "2603.28069"
      },
      "record_updated_at": "2026-03-30"
    },
    "genre": "preprint",
    "id": "arxiv:2603.28069",
    "issued": {
      "date-parts": [
        [
          2026,
          3,
          30
        ]
      ]
    },
    "note": "First published: 2026-03-30; Recorded arXiv version: v1; Recorded version updated: 2026-03-30T06:15:06Z.",
    "title": "MolmoPoint: Better Pointing for VLMs with Grounding Tokens",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2604.00886v1",
    "archive": "arXiv",
    "archive_location": "2604.00886",
    "author": [
      {
        "literal": "Nan Wang"
      },
      {
        "literal": "Zhiwei Jin"
      },
      {
        "literal": "Chen Chen"
      },
      {
        "literal": "Haonan Lu"
      }
    ],
    "citation-key": "arxiv_2604_00886",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "ce7f70ff1f8c7d4058d8fdf00cb6cf1d61c0367a50ba76fc96d356bb07452c60",
        "submitted_at": "2026-04-01T13:33:27Z",
        "updated_at": "2026-04-01T13:33:27Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2604.00886v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2604.00886",
      "catalog_id": "arxiv:2604.00886",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "adjacent",
      "first_published_at": "2026-04-01",
      "identifiers": {
        "arxiv": "2604.00886"
      },
      "record_updated_at": "2026-04-01"
    },
    "genre": "preprint",
    "id": "arxiv:2604.00886",
    "issued": {
      "date-parts": [
        [
          2026,
          4,
          1
        ]
      ]
    },
    "note": "First published: 2026-04-01; Recorded arXiv version: v1; Recorded version updated: 2026-04-01T13:33:27Z.",
    "title": "PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2604.06995v3",
    "archive": "arXiv",
    "archive_location": "2604.06995",
    "author": [
      {
        "literal": "Songze Li"
      },
      {
        "literal": "Xiaoke Guo"
      },
      {
        "literal": "Tianqi Liu"
      },
      {
        "literal": "Biao Yi"
      },
      {
        "literal": "Zhaoyan Gong"
      },
      {
        "literal": "Zhiqiang Liu"
      },
      {
        "literal": "Huajun Chen"
      },
      {
        "literal": "Wen Zhang"
      }
    ],
    "citation-key": "arxiv_2604_06995",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "b99643e43c5e20af088d6fa62152e03256c947af76a6b3c0abfc6f74a0f7d648",
        "submitted_at": "2026-04-08T12:12:09Z",
        "updated_at": "2026-10-02T06:30:10Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2604.06995v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2604.06995",
      "catalog_id": "arxiv:2604.06995",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-04-08",
      "identifiers": {
        "arxiv": "2604.06995"
      },
      "record_updated_at": "2026-10-02"
    },
    "genre": "preprint",
    "id": "arxiv:2604.06995",
    "issued": {
      "date-parts": [
        [
          2026,
          4,
          8
        ]
      ]
    },
    "note": "First published: 2026-04-08; Recorded arXiv version: v3; Recorded version updated: 2026-10-02T06:30:10Z.",
    "title": "What's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2604.13019v3",
    "archive": "arXiv",
    "archive_location": "2604.13019",
    "author": [
      {
        "literal": "Himangi Mittal"
      },
      {
        "literal": "Gaurav Mittal"
      },
      {
        "literal": "Nelson Daniel Troncoso"
      },
      {
        "literal": "Yu Hu"
      }
    ],
    "citation-key": "arxiv_2604_13019",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "aa89e3a09c0ce8b09bdb932f3f00bd2dccf8af4da11a727e675ddf8b2c578146",
        "submitted_at": "2026-04-14T17:55:46Z",
        "updated_at": "2026-05-28T06:47:16Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2604.13019v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2604.13019",
      "catalog_id": "arxiv:2604.13019",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-04-14",
      "identifiers": {
        "arxiv": "2604.13019"
      },
      "record_updated_at": "2026-05-28"
    },
    "genre": "preprint",
    "id": "arxiv:2604.13019",
    "issued": {
      "date-parts": [
        [
          2026,
          4,
          14
        ]
      ]
    },
    "note": "First published: 2026-04-14; Recorded arXiv version: v3; Recorded version updated: 2026-05-28T06:47:16Z.",
    "title": "PrecisionCUA: Iterative Visual Refinement for Pixel-Precise Cursor Grounding in Code Editors",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2604.17817v1",
    "archive": "arXiv",
    "archive_location": "2604.17817",
    "author": [
      {
        "literal": "Shiquan Zhang"
      },
      {
        "literal": "Tianyi Zhang"
      },
      {
        "literal": "Le Fang"
      },
      {
        "literal": "Simon D'Alfonso"
      },
      {
        "literal": "Hong Jia"
      },
      {
        "literal": "Vassilis Kostakos"
      }
    ],
    "citation-key": "arxiv_2604_17817",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "176f4d68e2f5084bee1938ee1399978052cdce2d2250ef06c16ddbf49c977da1",
        "submitted_at": "2026-04-20T05:15:14Z",
        "updated_at": "2026-04-20T05:15:14Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2604.17817v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2604.17817",
      "catalog_id": "arxiv:2604.17817",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-04-20",
      "identifiers": {
        "arxiv": "2604.17817"
      },
      "record_updated_at": "2026-04-20"
    },
    "genre": "preprint",
    "id": "arxiv:2604.17817",
    "issued": {
      "date-parts": [
        [
          2026,
          4,
          20
        ]
      ]
    },
    "note": "First published: 2026-04-20; Recorded arXiv version: v1; Recorded version updated: 2026-04-20T05:15:14Z.",
    "title": "Do LLMs Need to See Everything? A Benchmark and Study of Failures in LLM-driven Smartphone Automation using Screentext vs. Screenshots",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2604.24441v1",
    "archive": "arXiv",
    "archive_location": "2604.24441",
    "author": [
      {
        "literal": "Hongxin Li"
      },
      {
        "literal": "Xiping Wang"
      },
      {
        "literal": "Jingran Su"
      },
      {
        "literal": "Zheng Ju"
      },
      {
        "literal": "Yuntao Chen"
      },
      {
        "literal": "Qing Li"
      },
      {
        "literal": "Zhaoxiang Zhang"
      }
    ],
    "citation-key": "arxiv_2604_24441",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "65325912365effe8adbc39301a378d7526c60d1185691f3a89cb8acd4aa53c3f",
        "submitted_at": "2026-04-27T13:06:27Z",
        "updated_at": "2026-04-27T13:06:27Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2604.24441v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2604.24441",
      "catalog_id": "arxiv:2604.24441",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-04-27",
      "identifiers": {
        "arxiv": "2604.24441"
      },
      "record_updated_at": "2026-04-27"
    },
    "genre": "preprint",
    "id": "arxiv:2604.24441",
    "issued": {
      "date-parts": [
        [
          2026,
          4,
          27
        ]
      ]
    },
    "note": "First published: 2026-04-27; Recorded arXiv version: v1; Recorded version updated: 2026-04-27T13:06:27Z.",
    "title": "AutoGUI-v2: A Comprehensive Multi-Modal GUI Functionality Understanding Benchmark",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2604.25562v1",
    "archive": "arXiv",
    "archive_location": "2604.25562",
    "author": [
      {
        "literal": "Mengyao Du"
      },
      {
        "literal": "Han Fang"
      },
      {
        "literal": "Haokai Ma"
      },
      {
        "literal": "Jiahao Chen"
      },
      {
        "literal": "Kai Xu"
      },
      {
        "literal": "Quanjun Yin"
      },
      {
        "literal": "Ee-Chien Chang"
      }
    ],
    "citation-key": "arxiv_2604_25562",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "d2610c2658221d7da0bd888bf7b143ca6c4175791058570f6562cfa0c8c3a946",
        "submitted_at": "2026-04-28T12:32:21Z",
        "updated_at": "2026-04-28T12:32:21Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2604.25562v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2604.25562",
      "catalog_id": "arxiv:2604.25562",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-04-28",
      "identifiers": {
        "arxiv": "2604.25562"
      },
      "record_updated_at": "2026-04-28"
    },
    "genre": "preprint",
    "id": "arxiv:2604.25562",
    "issued": {
      "date-parts": [
        [
          2026,
          4,
          28
        ]
      ]
    },
    "note": "First published: 2026-04-28; Recorded arXiv version: v1; Recorded version updated: 2026-04-28T12:32:21Z.",
    "title": "SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2604.26148v3",
    "archive": "arXiv",
    "archive_location": "2604.26148",
    "author": [
      {
        "literal": "Chen Liang"
      },
      {
        "literal": "Xirui Jiang"
      },
      {
        "literal": "Naihao Deng"
      },
      {
        "literal": "Eytan Adar"
      },
      {
        "literal": "Anhong Guo"
      }
    ],
    "citation-key": "arxiv_2604_26148",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "5b572e37eefab40a6a21fa4e4589324380ad9f66873a4da5746fc0f46aaeb1f6",
        "submitted_at": "2026-04-28T22:15:06Z",
        "updated_at": "2026-08-11T15:48:53Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2604.26148v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2604.26148",
      "catalog_id": "arxiv:2604.26148",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-04-28",
      "identifiers": {
        "arxiv": "2604.26148"
      },
      "record_updated_at": "2026-08-11"
    },
    "genre": "preprint",
    "id": "arxiv:2604.26148",
    "issued": {
      "date-parts": [
        [
          2026,
          4,
          28
        ]
      ]
    },
    "note": "First published: 2026-04-28; Recorded arXiv version: v3; Recorded version updated: 2026-08-11T15:48:53Z.",
    "title": "Beyond Screenshots: Evaluating VLMs' Understanding of UI Animations",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2605.00551v1",
    "archive": "arXiv",
    "archive_location": "2605.00551",
    "author": [
      {
        "literal": "Michito Takeshita"
      },
      {
        "literal": "Takuro Kawada"
      },
      {
        "literal": "Takumi Ohashi"
      },
      {
        "literal": "Shunsuke Kitada"
      },
      {
        "literal": "Hitoshi Iyatomi"
      }
    ],
    "citation-key": "arxiv_2605_00551",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "87ef518590e29328ce752791df974c9e2215eac656fcf43fed97dd3e847f3cf7",
        "submitted_at": "2026-05-01T10:16:00Z",
        "updated_at": "2026-05-01T10:16:00Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2605.00551v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2605.00551",
      "catalog_id": "arxiv:2605.00551",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-05-01",
      "identifiers": {
        "arxiv": "2605.00551"
      },
      "record_updated_at": "2026-05-01"
    },
    "genre": "preprint",
    "id": "arxiv:2605.00551",
    "issued": {
      "date-parts": [
        [
          2026,
          5,
          1
        ]
      ]
    },
    "note": "First published: 2026-05-01; Recorded arXiv version: v1; Recorded version updated: 2026-05-01T10:16:00Z.",
    "title": "A11y-Compressor: A Framework for Enhancing the Efficiency of GUI Agent Observations through Visual Context Reconstruction and Redundancy Reduction",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2605.02630v1",
    "archive": "arXiv",
    "archive_location": "2605.02630",
    "author": [
      {
        "literal": "Ruilin Yao"
      },
      {
        "literal": "Shegnwu Xiong"
      },
      {
        "literal": "Tianyu Zou"
      },
      {
        "literal": "Shili Xiong"
      },
      {
        "literal": "Yi Rong"
      }
    ],
    "citation-key": "arxiv_2605_02630",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "2dc8c2f5a5a97bc372a1bf5ab3fe0537e53a681f808d45877f55cdef6556858c",
        "submitted_at": "2026-05-04T14:18:46Z",
        "updated_at": "2026-05-04T14:18:46Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2605.02630v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2605.02630",
      "catalog_id": "arxiv:2605.02630",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-05-04",
      "identifiers": {
        "arxiv": "2605.02630"
      },
      "record_updated_at": "2026-05-04"
    },
    "genre": "preprint",
    "id": "arxiv:2605.02630",
    "issued": {
      "date-parts": [
        [
          2026,
          5,
          4
        ]
      ]
    },
    "note": "First published: 2026-05-04; Recorded arXiv version: v1; Recorded version updated: 2026-05-04T14:18:46Z.",
    "title": "AutoFocus: Uncertainty-Aware Active Visual Search for GUI Grounding",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2605.07134v1",
    "archive": "arXiv",
    "archive_location": "2605.07134",
    "author": [
      {
        "literal": "Donguk Kwon"
      },
      {
        "literal": "Dongha Lee"
      }
    ],
    "citation-key": "arxiv_2605_07134",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "6bf74d53b22530951788bd329167f5ba9474827c712590ae9c6d316fac4d62bc",
        "submitted_at": "2026-05-08T02:11:23Z",
        "updated_at": "2026-05-08T02:11:23Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2605.07134v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2605.07134",
      "catalog_id": "arxiv:2605.07134",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-05-08",
      "identifiers": {
        "arxiv": "2605.07134"
      },
      "record_updated_at": "2026-05-08"
    },
    "genre": "preprint",
    "id": "arxiv:2605.07134",
    "issued": {
      "date-parts": [
        [
          2026,
          5,
          8
        ]
      ]
    },
    "note": "First published: 2026-05-08; Recorded arXiv version: v1; Recorded version updated: 2026-05-08T02:11:23Z.",
    "title": "Region4Web: Rethinking Observation Space Granularity for Web Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2605.11212v3",
    "archive": "arXiv",
    "archive_location": "2605.11212",
    "author": [
      {
        "literal": "Amirhossein Abaskohi"
      },
      {
        "literal": "Yuhang He"
      },
      {
        "literal": "Peter West"
      },
      {
        "literal": "Giuseppe Carenini"
      },
      {
        "literal": "Pranit Chawla"
      },
      {
        "literal": "Vibhav Vineet"
      }
    ],
    "citation-key": "arxiv_2605_11212",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "422d2fdf2d7f665df1a5672e03d837ba41fe9c6832d64c40317f77481f642130",
        "submitted_at": "2026-05-11T20:27:54Z",
        "updated_at": "2026-06-05T22:18:46Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2605.11212v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2605.11212",
      "catalog_id": "arxiv:2605.11212",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-05-11",
      "identifiers": {
        "arxiv": "2605.11212"
      },
      "record_updated_at": "2026-06-05"
    },
    "genre": "preprint",
    "id": "arxiv:2605.11212",
    "issued": {
      "date-parts": [
        [
          2026,
          5,
          11
        ]
      ]
    },
    "note": "First published: 2026-05-11; Recorded arXiv version: v3; Recorded version updated: 2026-06-05T22:18:46Z.",
    "title": "ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2605.12549v1",
    "archive": "arXiv",
    "archive_location": "2605.12549",
    "author": [
      {
        "literal": "Jiaping Lin"
      },
      {
        "literal": "Fei Shen"
      },
      {
        "literal": "Junzhe Li"
      },
      {
        "literal": "Ping Nie"
      },
      {
        "literal": "Fei Yu"
      },
      {
        "literal": "Ming Li"
      },
      {
        "literal": "Haizhou Li"
      }
    ],
    "citation-key": "arxiv_2605_12549",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "cb60b76fca3a8825030b1a31a7b97ff31e06f30ac3852f243efe440f965e5578",
        "submitted_at": "2026-05-10T07:04:07Z",
        "updated_at": "2026-05-10T07:04:07Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2605.12549v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2605.12549",
      "catalog_id": "arxiv:2605.12549",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-05-10",
      "identifiers": {
        "arxiv": "2605.12549"
      },
      "record_updated_at": "2026-05-10"
    },
    "genre": "preprint",
    "id": "arxiv:2605.12549",
    "issued": {
      "date-parts": [
        [
          2026,
          5,
          10
        ]
      ]
    },
    "note": "First published: 2026-05-10; Recorded arXiv version: v1; Recorded version updated: 2026-05-10T07:04:07Z.",
    "title": "What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2605.15542v1",
    "archive": "arXiv",
    "archive_location": "2605.15542",
    "author": [
      {
        "literal": "Yichao Liu"
      },
      {
        "literal": "Huawen Shen"
      },
      {
        "literal": "Liu Yu"
      },
      {
        "literal": "Shiyu Liu"
      },
      {
        "literal": "Zeyu Chen"
      },
      {
        "literal": "Yu Zhou"
      }
    ],
    "citation-key": "arxiv_2605_15542",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "fd85c0d0a8b6bc5c687bc301b1b84d6a019c5713012890e0a23c08ae2d83a1e6",
        "submitted_at": "2026-05-15T02:27:41Z",
        "updated_at": "2026-05-15T02:27:41Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2605.15542v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2605.15542",
      "catalog_id": "arxiv:2605.15542",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-05-15",
      "identifiers": {
        "arxiv": "2605.15542"
      },
      "record_updated_at": "2026-05-15"
    },
    "genre": "preprint",
    "id": "arxiv:2605.15542",
    "issued": {
      "date-parts": [
        [
          2026,
          5,
          15
        ]
      ]
    },
    "note": "First published: 2026-05-15; Recorded arXiv version: v1; Recorded version updated: 2026-05-15T02:27:41Z.",
    "title": "DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2605.17656v1",
    "archive": "arXiv",
    "archive_location": "2605.17656",
    "author": [
      {
        "literal": "Athar Parvez"
      },
      {
        "literal": "Muhammad Jawad Mufti"
      },
      {
        "literal": "Muqaddas Gull"
      },
      {
        "literal": "Omar Hammad"
      }
    ],
    "citation-key": "arxiv_2605_17656",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "ff95e0b071508592190ba236741c1c01200dd38fdc74c31b2cc4d1bf8143ae9c",
        "submitted_at": "2026-05-17T21:14:32Z",
        "updated_at": "2026-05-17T21:14:32Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2605.17656v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2605.17656",
      "catalog_id": "arxiv:2605.17656",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-05-17",
      "identifiers": {
        "arxiv": "2605.17656"
      },
      "record_updated_at": "2026-05-17"
    },
    "genre": "preprint",
    "id": "arxiv:2605.17656",
    "issued": {
      "date-parts": [
        [
          2026,
          5,
          17
        ]
      ]
    },
    "note": "First published: 2026-05-17; Recorded arXiv version: v1; Recorded version updated: 2026-05-17T21:14:32Z.",
    "title": "MUIAnno: An Expert-Annotated Dataset and Evaluation Benchmark for Mobile UI Understanding",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2606.01790v1",
    "archive": "arXiv",
    "archive_location": "2606.01790",
    "author": [
      {
        "literal": "Yuhang Han"
      },
      {
        "literal": "Wenzheng Yang"
      },
      {
        "literal": "Yujie Chen"
      },
      {
        "literal": "Xiangqi Jin"
      },
      {
        "literal": "Yaojie Zhang"
      },
      {
        "literal": "Siteng Huang"
      },
      {
        "literal": "Linfeng Zhang"
      }
    ],
    "citation-key": "arxiv_2606_01790",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "73364572c0f21976048c89cd7732a16c7a952b08986792d02681a5ad0288c3ca",
        "submitted_at": "2026-06-01T07:10:00Z",
        "updated_at": "2026-06-01T07:10:00Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2606.01790v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.01790",
      "catalog_id": "arxiv:2606.01790",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-01",
      "identifiers": {
        "arxiv": "2606.01790"
      },
      "record_updated_at": "2026-06-01"
    },
    "genre": "preprint",
    "id": "arxiv:2606.01790",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          1
        ]
      ]
    },
    "note": "First published: 2026-06-01; Recorded arXiv version: v1; Recorded version updated: 2026-06-01T07:10:00Z.",
    "title": "STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2606.04701v1",
    "archive": "arXiv",
    "archive_location": "2606.04701",
    "author": [
      {
        "literal": "Jiashu Yao"
      },
      {
        "literal": "Heyan Huang"
      },
      {
        "literal": "Daiqing Wu"
      },
      {
        "literal": "Wangke Chen"
      },
      {
        "literal": "Huaxi Ai"
      },
      {
        "literal": "Haoyu Wen"
      },
      {
        "literal": "Zeming Liu"
      },
      {
        "literal": "Yuhang Guo"
      }
    ],
    "citation-key": "arxiv_2606_04701",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "4d5a90333c4f6be0b8d203a2f5938f7e7eefcb09fbe7ea47b85eba8c7c1c422a",
        "submitted_at": "2026-06-03T10:25:46Z",
        "updated_at": "2026-06-03T10:25:46Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2606.04701v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.04701",
      "catalog_id": "arxiv:2606.04701",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-03",
      "identifiers": {
        "arxiv": "2606.04701"
      },
      "record_updated_at": "2026-06-03"
    },
    "genre": "preprint",
    "id": "arxiv:2606.04701",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          3
        ]
      ]
    },
    "note": "First published: 2026-06-03; Recorded arXiv version: v1; Recorded version updated: 2026-06-03T10:25:46Z.",
    "title": "Benchmarking Living-Screen-Native GUI Agents on Short-Video Platforms",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2606.06322v1",
    "archive": "arXiv",
    "archive_location": "2606.06322",
    "author": [
      {
        "literal": "Nathan Bout"
      },
      {
        "literal": "Maxime Langevin"
      },
      {
        "literal": "Ronan Riochet"
      }
    ],
    "citation-key": "arxiv_2606_06322",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "27ffcb10d966946de9fa2353c4b96798e5f090bdfdc5610f5e8a5c6233cf70ea",
        "submitted_at": "2026-06-04T15:57:29Z",
        "updated_at": "2026-06-04T15:57:29Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2606.06322v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.06322",
      "catalog_id": "arxiv:2606.06322",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-04",
      "identifiers": {
        "arxiv": "2606.06322"
      },
      "record_updated_at": "2026-06-04"
    },
    "genre": "preprint",
    "id": "arxiv:2606.06322",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          4
        ]
      ]
    },
    "note": "First published: 2026-06-04; Recorded arXiv version: v1; Recorded version updated: 2026-06-04T15:57:29Z.",
    "title": "DragOn: A Benchmark and Dataset for Drag-Based GUI Interactions",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2606.06708v2",
    "archive": "arXiv",
    "archive_location": "2606.06708",
    "author": [
      {
        "literal": "Shubham Gaur"
      },
      {
        "literal": "Ian Lane"
      }
    ],
    "citation-key": "arxiv_2606_06708",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "a449bb2706d5d18cbd176dcfd2f14d814cf1c1a22a08e9210c99e0722e10ea93",
        "submitted_at": "2026-06-04T20:48:37Z",
        "updated_at": "2026-08-04T18:57:23Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2606.06708v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.06708",
      "catalog_id": "arxiv:2606.06708",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-04",
      "identifiers": {
        "arxiv": "2606.06708"
      },
      "record_updated_at": "2026-08-04"
    },
    "genre": "preprint",
    "id": "arxiv:2606.06708",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          4
        ]
      ]
    },
    "note": "First published: 2026-06-04; Recorded arXiv version: v2; Recorded version updated: 2026-08-04T18:57:23Z.",
    "title": "Signal-Driven Observation for Long-Horizon Web Agents",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2606.12666v2",
    "archive": "arXiv",
    "archive_location": "2606.12666",
    "author": [
      {
        "literal": "Siyu Shen"
      },
      {
        "literal": "Fenghao Xu"
      },
      {
        "literal": "Wenrui Diao"
      },
      {
        "literal": "Kehuan Zhang"
      }
    ],
    "citation-key": "arxiv_2606_12666",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "fed1c6e109cc5d34aebe3bb333955e8bf792264d4c1ed0893d76534a77649afd",
        "submitted_at": "2026-06-10T20:48:39Z",
        "updated_at": "2026-06-16T03:15:00Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2606.12666v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.12666",
      "catalog_id": "arxiv:2606.12666",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-10",
      "identifiers": {
        "arxiv": "2606.12666"
      },
      "record_updated_at": "2026-06-16"
    },
    "genre": "preprint",
    "id": "arxiv:2606.12666",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          10
        ]
      ]
    },
    "note": "First published: 2026-06-10; Recorded arXiv version: v2; Recorded version updated: 2026-06-16T03:15:00Z.",
    "title": "CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2606.18448v1",
    "archive": "arXiv",
    "archive_location": "2606.18448",
    "author": [
      {
        "literal": "Ziyan Jiang"
      },
      {
        "literal": "Li An"
      },
      {
        "literal": "Yujian Liu"
      },
      {
        "literal": "Jiabao Ji"
      },
      {
        "literal": "Qiucheng Wu"
      },
      {
        "literal": "Jacob Andreas"
      },
      {
        "literal": "Yang Zhang"
      },
      {
        "literal": "Shiyu Chang"
      }
    ],
    "citation-key": "arxiv_2606_18448",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "2605cedb4359aa0cf1e694455903871ed334dd37b7b8e15edf31bac9d5e51b13",
        "submitted_at": "2026-06-16T19:57:07Z",
        "updated_at": "2026-06-16T19:57:07Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2606.18448v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.18448",
      "catalog_id": "arxiv:2606.18448",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-16",
      "identifiers": {
        "arxiv": "2606.18448"
      },
      "record_updated_at": "2026-06-16"
    },
    "genre": "preprint",
    "id": "arxiv:2606.18448",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          16
        ]
      ]
    },
    "note": "First published: 2026-06-16; Recorded arXiv version: v1; Recorded version updated: 2026-06-16T19:57:07Z.",
    "title": "VISUALSKILL: Multimodal Skills for Computer-Use Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2606.29472v1",
    "archive": "arXiv",
    "archive_location": "2606.29472",
    "author": [
      {
        "literal": "Bojie Li"
      },
      {
        "literal": "Noah Shi"
      }
    ],
    "citation-key": "arxiv_2606_29472",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "54de4e93f4f3e39d904b4661a193765e02c29f8ec7787264aee5616579c32210",
        "submitted_at": "2026-06-28T15:59:31Z",
        "updated_at": "2026-06-28T15:59:31Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2606.29472v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.29472",
      "catalog_id": "arxiv:2606.29472",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-28",
      "identifiers": {
        "arxiv": "2606.29472"
      },
      "record_updated_at": "2026-06-28"
    },
    "genre": "preprint",
    "id": "arxiv:2606.29472",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          28
        ]
      ]
    },
    "note": "First published: 2026-06-28; Recorded arXiv version: v1; Recorded version updated: 2026-06-28T15:59:31Z.",
    "title": "Agent-Computer Observation Interfaces Enable Dynamic Computer Use",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2606.29705v1",
    "archive": "arXiv",
    "archive_location": "2606.29705",
    "author": [
      {
        "literal": "Sunqi Fan"
      },
      {
        "literal": "Lingshan Chen"
      },
      {
        "literal": "Runqi Yin"
      },
      {
        "literal": "Qingle Liu"
      },
      {
        "literal": "Yongming Rao"
      },
      {
        "literal": "Meng-Hao Guo"
      },
      {
        "literal": "Shi-Min Hu"
      }
    ],
    "citation-key": "arxiv_2606_29705",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "7beb70ac91463b77a8babaf2b077c46c5072e8f86d22f4d9afc9c1e77680f309",
        "submitted_at": "2026-06-29T02:16:21Z",
        "updated_at": "2026-06-29T02:16:21Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2606.29705v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.29705",
      "catalog_id": "arxiv:2606.29705",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-29",
      "identifiers": {
        "arxiv": "2606.29705"
      },
      "record_updated_at": "2026-06-29"
    },
    "genre": "preprint",
    "id": "arxiv:2606.29705",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          29
        ]
      ]
    },
    "note": "First published: 2026-06-29; Recorded arXiv version: v1; Recorded version updated: 2026-06-29T02:16:21Z.",
    "title": "GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2606.30084v1",
    "archive": "arXiv",
    "archive_location": "2606.30084",
    "author": [
      {
        "literal": "Chen Liu"
      },
      {
        "literal": "Ling Chen"
      },
      {
        "literal": "Hanzhang Zhou"
      },
      {
        "literal": "Liangyu Chen"
      },
      {
        "literal": "Chenglin Cai"
      },
      {
        "literal": "Xin Yu"
      },
      {
        "literal": "Steven Hoi"
      },
      {
        "literal": "Yue Wang"
      }
    ],
    "citation-key": "arxiv_2606_30084",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "50e44e08750d4152f9b5408885f8a6a016c5f789af9712e447ee147fb25adb8d",
        "submitted_at": "2026-06-29T10:20:39Z",
        "updated_at": "2026-06-29T10:20:39Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2606.30084v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.30084",
      "catalog_id": "arxiv:2606.30084",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-29",
      "identifiers": {
        "arxiv": "2606.30084"
      },
      "record_updated_at": "2026-06-29"
    },
    "genre": "preprint",
    "id": "arxiv:2606.30084",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          29
        ]
      ]
    },
    "note": "First published: 2026-06-29; Recorded arXiv version: v1; Recorded version updated: 2026-06-29T10:20:39Z.",
    "title": "One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2606.30697v1",
    "archive": "arXiv",
    "archive_location": "2606.30697",
    "author": [
      {
        "literal": "Yogeswar Reddy Thota"
      }
    ],
    "citation-key": "arxiv_2606_30697",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "6f3f2ae1438986c11146fec508dd61fd3e848ddcbf830f86a7dfa759280d730a",
        "submitted_at": "2026-06-29T03:19:40Z",
        "updated_at": "2026-06-29T03:19:40Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2606.30697v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.30697",
      "catalog_id": "arxiv:2606.30697",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-29",
      "identifiers": {
        "arxiv": "2606.30697"
      },
      "record_updated_at": "2026-06-29"
    },
    "genre": "preprint",
    "id": "arxiv:2606.30697",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          29
        ]
      ]
    },
    "note": "First published: 2026-06-29; Recorded arXiv version: v1; Recorded version updated: 2026-06-29T03:19:40Z.",
    "title": "LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2607.04334v2",
    "archive": "arXiv",
    "archive_location": "2607.04334",
    "author": [
      {
        "literal": "Guijia Zhang"
      },
      {
        "literal": "Yuxun Chen"
      },
      {
        "literal": "Yuheng Qi"
      },
      {
        "literal": "Harry Yang"
      }
    ],
    "citation-key": "arxiv_2607_04334",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "e7fdae5d6e5ea17639fe0e2b8e2d655df7201a438d84acdeb3e0d02a78051ae2",
        "submitted_at": "2026-07-05T14:33:29Z",
        "updated_at": "2026-07-18T16:56:38Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2607.04334v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2607.04334",
      "catalog_id": "arxiv:2607.04334",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-07-05",
      "identifiers": {
        "arxiv": "2607.04334"
      },
      "record_updated_at": "2026-07-18"
    },
    "genre": "preprint",
    "id": "arxiv:2607.04334",
    "issued": {
      "date-parts": [
        [
          2026,
          7,
          5
        ]
      ]
    },
    "note": "First published: 2026-07-05; Recorded arXiv version: v2; Recorded version updated: 2026-07-18T16:56:38Z.",
    "title": "Do GUI Agents Believe Their Eyes? Diagnosing State-Belief Reliance on Pixels versus Structure",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2607.26041v2",
    "archive": "arXiv",
    "archive_location": "2607.26041",
    "author": [
      {
        "literal": "Abhishek Pillai"
      },
      {
        "literal": "Samir Kumar Nayak"
      },
      {
        "literal": "Yuan Chen"
      }
    ],
    "citation-key": "arxiv_2607_26041",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "352c892a52692301e14125e126a52508feb39ef7cd034d7cb0c48a27fb54b8ac",
        "submitted_at": "2026-07-28T17:49:51Z",
        "updated_at": "2026-07-29T19:07:50Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2607.26041v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2607.26041",
      "catalog_id": "arxiv:2607.26041",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-07-28",
      "identifiers": {
        "arxiv": "2607.26041"
      },
      "record_updated_at": "2026-07-29"
    },
    "genre": "preprint",
    "id": "arxiv:2607.26041",
    "issued": {
      "date-parts": [
        [
          2026,
          7,
          28
        ]
      ]
    },
    "note": "First published: 2026-07-28; Recorded arXiv version: v2; Recorded version updated: 2026-07-29T19:07:50Z.",
    "title": "Desktop-Delta Bench: Do Computer-Use Models Understand Desktop GUI Transitions?",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2608.03270v1",
    "archive": "arXiv",
    "archive_location": "2608.03270",
    "author": [
      {
        "literal": "Zichuan Fu"
      },
      {
        "literal": "Shirong Wang"
      },
      {
        "literal": "Wenlin Zhang"
      },
      {
        "literal": "Guojing Li"
      },
      {
        "literal": "Yimin Deng"
      },
      {
        "literal": "Jingtong Gao"
      },
      {
        "literal": "Junjia Qi"
      },
      {
        "literal": "Hanyu Yan"
      },
      {
        "literal": "Yefeng Zheng"
      },
      {
        "literal": "Xiaopeng Li"
      },
      {
        "literal": "Wanyu Wang"
      },
      {
        "literal": "Xian Wu"
      },
      {
        "literal": "Xiangyu Zhao"
      }
    ],
    "citation-key": "arxiv_2608_03270",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "fb64bb5faa37e68b35a2398ad896fc02181a4d2749a3067391e6b3bf023a0f48",
        "submitted_at": "2026-08-04T07:47:37Z",
        "updated_at": "2026-08-04T07:47:37Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2608.03270v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2608.03270",
      "catalog_id": "arxiv:2608.03270",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-08-04",
      "identifiers": {
        "arxiv": "2608.03270"
      },
      "record_updated_at": "2026-08-04"
    },
    "genre": "preprint",
    "id": "arxiv:2608.03270",
    "issued": {
      "date-parts": [
        [
          2026,
          8,
          4
        ]
      ]
    },
    "note": "First published: 2026-08-04; Recorded arXiv version: v1; Recorded version updated: 2026-08-04T07:47:37Z.",
    "title": "GUI-Lens: Coarse-to-Fine Cropping for GUI Grounding with General-Purpose VLMs",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2608.06171v1",
    "archive": "arXiv",
    "archive_location": "2608.06171",
    "author": [
      {
        "literal": "Jiaming Wei"
      },
      {
        "literal": "Zekun Wu"
      },
      {
        "literal": "Adriano Koshiyama"
      },
      {
        "literal": "Maria Perez-Ortiz"
      }
    ],
    "citation-key": "arxiv_2608_06171",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "9055ec9c70777fc94179983d82bf841bac12332ebed7f49342883c8d842d0fbc",
        "submitted_at": "2026-08-06T15:37:04Z",
        "updated_at": "2026-08-06T15:37:04Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2608.06171v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2608.06171",
      "catalog_id": "arxiv:2608.06171",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-08-06",
      "identifiers": {
        "arxiv": "2608.06171"
      },
      "record_updated_at": "2026-08-06"
    },
    "genre": "preprint",
    "id": "arxiv:2608.06171",
    "issued": {
      "date-parts": [
        [
          2026,
          8,
          6
        ]
      ]
    },
    "note": "First published: 2026-08-06; Recorded arXiv version: v1; Recorded version updated: 2026-08-06T15:37:04Z.",
    "title": "Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2608.08392v1",
    "archive": "arXiv",
    "archive_location": "2608.08392",
    "author": [
      {
        "literal": "Zejun Xu"
      },
      {
        "literal": "Taiyi Chen"
      },
      {
        "literal": "Jin Li"
      },
      {
        "literal": "Yongtong Gu"
      },
      {
        "literal": "Qi Cheng"
      },
      {
        "literal": "Aixuan Lv"
      },
      {
        "literal": "Shuai Zhu"
      },
      {
        "literal": "Pengfei Zhu"
      },
      {
        "literal": "Kaichen Yang"
      },
      {
        "literal": "Boyu Sun"
      },
      {
        "literal": "Yixian Yang"
      },
      {
        "literal": "Mulong Xie"
      },
      {
        "literal": "Xin Liu"
      },
      {
        "literal": "Dagang Li"
      },
      {
        "literal": "Xiaoteng Ma"
      },
      {
        "literal": "Hongru Wang"
      }
    ],
    "citation-key": "arxiv_2608_08392",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "d0e469cd7d84080e11df46d826460bea79eae71b8fa5786cacd96aac02b8b0a8",
        "submitted_at": "2026-08-09T01:08:19Z",
        "updated_at": "2026-08-09T01:08:19Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2608.08392v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2608.08392",
      "catalog_id": "arxiv:2608.08392",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-08-09",
      "identifiers": {
        "arxiv": "2608.08392"
      },
      "record_updated_at": "2026-08-09"
    },
    "genre": "preprint",
    "id": "arxiv:2608.08392",
    "issued": {
      "date-parts": [
        [
          2026,
          8,
          9
        ]
      ]
    },
    "note": "First published: 2026-08-09; Recorded arXiv version: v1; Recorded version updated: 2026-08-09T01:08:19Z.",
    "title": "CAP: A Scalable Benchmark for Evaluating Cross-Site Browser Agents with Complex Actions and Perception",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2608.08939v1",
    "archive": "arXiv",
    "archive_location": "2608.08939",
    "author": [
      {
        "literal": "Rahul Deivasigamani"
      },
      {
        "literal": "Sayeda Faatin Alvi"
      },
      {
        "literal": "Derqui Andrea"
      },
      {
        "literal": "Kaushal Punjabi"
      },
      {
        "literal": "Stjepan Picek"
      }
    ],
    "citation-key": "arxiv_2608_08939",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "64e4845ce85dd67b7790cf5de357f12deb72b71eb72031298e1064809099f063",
        "submitted_at": "2026-08-09T22:13:55Z",
        "updated_at": "2026-08-09T22:13:55Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2608.08939v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2608.08939",
      "catalog_id": "arxiv:2608.08939",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-08-09",
      "identifiers": {
        "arxiv": "2608.08939"
      },
      "record_updated_at": "2026-08-09"
    },
    "genre": "preprint",
    "id": "arxiv:2608.08939",
    "issued": {
      "date-parts": [
        [
          2026,
          8,
          9
        ]
      ]
    },
    "note": "First published: 2026-08-09; Recorded arXiv version: v1; Recorded version updated: 2026-08-09T22:13:55Z.",
    "title": "Not an A11y: How Android Accessibility Exposes Mobile AI Agents to Indirect Prompt Injection",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2608.09654v1",
    "archive": "arXiv",
    "archive_location": "2608.09654",
    "author": [
      {
        "literal": "Yuke Li"
      },
      {
        "literal": "Xuehan Hou"
      }
    ],
    "citation-key": "arxiv_2608_09654",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "f05f128cccb514987b7defb52c8f43b45d917e0e0f9570db4e75c4fe23b38533",
        "submitted_at": "2026-08-10T14:29:07Z",
        "updated_at": "2026-08-10T14:29:07Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2608.09654v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2608.09654",
      "catalog_id": "arxiv:2608.09654",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-08-10",
      "identifiers": {
        "arxiv": "2608.09654"
      },
      "record_updated_at": "2026-08-10"
    },
    "genre": "preprint",
    "id": "arxiv:2608.09654",
    "issued": {
      "date-parts": [
        [
          2026,
          8,
          10
        ]
      ]
    },
    "note": "First published: 2026-08-10; Recorded arXiv version: v1; Recorded version updated: 2026-08-10T14:29:07Z.",
    "title": "Hallucination-Free GUI Grounding via Regression-Free Layout-Aware Matching",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2608.18307v1",
    "archive": "arXiv",
    "archive_location": "2608.18307",
    "author": [
      {
        "literal": "Tianchen Guan"
      },
      {
        "literal": "Xinlei Lin"
      },
      {
        "literal": "Royce Cheng-Yue"
      },
      {
        "literal": "Xiangjun Wang"
      },
      {
        "literal": "Shuyan Zhou"
      }
    ],
    "citation-key": "arxiv_2608_18307",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "de4889c021f35c169092e17801fec414cce21b37c74a4ff72af6a6c67a1a0a25",
        "submitted_at": "2026-08-18T20:38:26Z",
        "updated_at": "2026-08-18T20:38:26Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2608.18307v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2608.18307",
      "catalog_id": "arxiv:2608.18307",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-08-18",
      "identifiers": {
        "arxiv": "2608.18307"
      },
      "record_updated_at": "2026-08-18"
    },
    "genre": "preprint",
    "id": "arxiv:2608.18307",
    "issued": {
      "date-parts": [
        [
          2026,
          8,
          18
        ]
      ]
    },
    "note": "First published: 2026-08-18; Recorded arXiv version: v1; Recorded version updated: 2026-08-18T20:38:26Z.",
    "title": "ComponentBench: Diagnosing Component-Level Failures in Computer-Use Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2608.21794v1",
    "archive": "arXiv",
    "archive_location": "2608.21794",
    "author": [
      {
        "literal": "Qijia Chen"
      },
      {
        "literal": "Giulio Jacucci"
      }
    ],
    "citation-key": "arxiv_2608_21794",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "cabd094270d01b20df7b029be29c5d460d10beb84e43e3e783f4f11997b74114",
        "submitted_at": "2026-08-22T06:30:03Z",
        "updated_at": "2026-08-22T06:30:03Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2608.21794v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2608.21794",
      "catalog_id": "arxiv:2608.21794",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-08-22",
      "identifiers": {
        "arxiv": "2608.21794"
      },
      "record_updated_at": "2026-08-22"
    },
    "genre": "preprint",
    "id": "arxiv:2608.21794",
    "issued": {
      "date-parts": [
        [
          2026,
          8,
          22
        ]
      ]
    },
    "note": "First published: 2026-08-22; Recorded arXiv version: v1; Recorded version updated: 2026-08-22T06:30:03Z.",
    "title": "Lexical Coupling in GUI Element Grounding: Sentence Embeddings Track Labels across Mobile and Web",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2608.21832v2",
    "archive": "arXiv",
    "archive_location": "2608.21832",
    "author": [
      {
        "literal": "Md Abrar Jahin"
      },
      {
        "literal": "Md Rizwan Parvez"
      }
    ],
    "citation-key": "arxiv_2608_21832",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "970441704314fabffc46cb4a340dd6e0bde0e84ab9b7fcd2db2c9a8be9dc61d8",
        "submitted_at": "2026-08-22T08:04:59Z",
        "updated_at": "2026-08-27T07:03:01Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2608.21832v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2608.21832",
      "catalog_id": "arxiv:2608.21832",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-08-22",
      "identifiers": {
        "arxiv": "2608.21832"
      },
      "record_updated_at": "2026-08-27"
    },
    "genre": "preprint",
    "id": "arxiv:2608.21832",
    "issued": {
      "date-parts": [
        [
          2026,
          8,
          22
        ]
      ]
    },
    "note": "First published: 2026-08-22; Recorded arXiv version: v2; Recorded version updated: 2026-08-27T07:03:01Z.",
    "title": "GUI-Primitives: Diagnosing Spatial Reasoning Failures in Vision-Language GUI Grounding",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2608.24015v1",
    "archive": "arXiv",
    "archive_location": "2608.24015",
    "author": [
      {
        "literal": "Yijie Ma"
      },
      {
        "literal": "Chaoyue Niu"
      },
      {
        "literal": "Fan Wu"
      },
      {
        "literal": "Guihai Chen"
      }
    ],
    "citation-key": "arxiv_2608_24015",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "a7e4fe2cb74124b2897d86a4fee32113164b86a8f5abae040bf77db4900e0bc4",
        "submitted_at": "2026-08-25T03:10:01Z",
        "updated_at": "2026-08-25T03:10:01Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2608.24015v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2608.24015",
      "catalog_id": "arxiv:2608.24015",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-08-25",
      "identifiers": {
        "arxiv": "2608.24015"
      },
      "record_updated_at": "2026-08-25"
    },
    "genre": "preprint",
    "id": "arxiv:2608.24015",
    "issued": {
      "date-parts": [
        [
          2026,
          8,
          25
        ]
      ]
    },
    "note": "First published: 2026-08-25; Recorded arXiv version: v1; Recorded version updated: 2026-08-25T03:10:01Z.",
    "title": "Reflection with Action-Induced Visual Differences for Desktop GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2609.10297v1",
    "archive": "arXiv",
    "archive_location": "2609.10297",
    "author": [
      {
        "literal": "Yuhao Wang"
      },
      {
        "literal": "Mu Qiao"
      },
      {
        "literal": "Xindong Zhang"
      },
      {
        "literal": "Yunzhi Zhuge"
      },
      {
        "literal": "Lei Zhang"
      },
      {
        "literal": "Huchuan Lu"
      }
    ],
    "citation-key": "arxiv_2609_10297",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "20d3bc3137e163f6b467b8c464101478b2375fbab8aebe9179e2e1113b34f503",
        "submitted_at": "2026-09-09T15:12:48Z",
        "updated_at": "2026-09-09T15:12:48Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2609.10297v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2609.10297",
      "catalog_id": "arxiv:2609.10297",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-09-09",
      "identifiers": {
        "arxiv": "2609.10297"
      },
      "record_updated_at": "2026-09-09"
    },
    "genre": "preprint",
    "id": "arxiv:2609.10297",
    "issued": {
      "date-parts": [
        [
          2026,
          9,
          9
        ]
      ]
    },
    "note": "First published: 2026-09-09; Recorded arXiv version: v1; Recorded version updated: 2026-09-09T15:12:48Z.",
    "title": "TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2609.13287v1",
    "archive": "arXiv",
    "archive_location": "2609.13287",
    "author": [
      {
        "literal": "Zhangxuan Gu"
      },
      {
        "literal": "Haoxing Chen"
      },
      {
        "literal": "Qi Qin"
      },
      {
        "literal": "Yi Xin"
      },
      {
        "literal": "Kai Gan"
      },
      {
        "literal": "Lin Liu"
      },
      {
        "literal": "Long Cui"
      },
      {
        "literal": "Xiaomei Wang"
      },
      {
        "literal": "Beitong Zhou"
      },
      {
        "literal": "Yunzhu Zhang"
      },
      {
        "literal": "Zhengwen Zeng"
      },
      {
        "literal": "Changlong Gao"
      },
      {
        "literal": "Weizhi Chen"
      },
      {
        "literal": "Rongchao Zhang"
      },
      {
        "literal": "Haoyuan Wu"
      },
      {
        "literal": "Shuheng Shen"
      },
      {
        "literal": "Changhua Meng"
      },
      {
        "literal": "Weiqiang Wang"
      },
      {
        "literal": "Jianguo Li"
      },
      {
        "literal": "Zhenzhong Lan"
      }
    ],
    "citation-key": "arxiv_2609_13287",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "2d7e9643c0543f088e5d2b17699c843a7643c611315f20ce92e83aea849b931a",
        "submitted_at": "2026-09-09T05:53:39Z",
        "updated_at": "2026-09-09T05:53:39Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2609.13287v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2609.13287",
      "catalog_id": "arxiv:2609.13287",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-09-09",
      "identifiers": {
        "arxiv": "2609.13287"
      },
      "record_updated_at": "2026-09-09"
    },
    "genre": "preprint",
    "id": "arxiv:2609.13287",
    "issued": {
      "date-parts": [
        [
          2026,
          9,
          9
        ]
      ]
    },
    "note": "First published: 2026-09-09; Recorded arXiv version: v1; Recorded version updated: 2026-09-09T05:53:39Z.",
    "title": "LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2609.13873v1",
    "archive": "arXiv",
    "archive_location": "2609.13873",
    "author": [
      {
        "literal": "Qihang Cen"
      },
      {
        "literal": "Tianshuo Cong"
      },
      {
        "literal": "Da Song"
      },
      {
        "literal": "Xinlei He"
      },
      {
        "literal": "Jiaxing Song"
      },
      {
        "literal": "Ke Xu"
      },
      {
        "literal": "Qi Li"
      }
    ],
    "citation-key": "arxiv_2609_13873",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "1eda33b358d4c4caf8c1fb0b1bd92698c3b37cee995d820f40ecffe82010edb4",
        "submitted_at": "2026-09-12T10:55:54Z",
        "updated_at": "2026-09-12T10:55:54Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2609.13873v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2609.13873",
      "catalog_id": "arxiv:2609.13873",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-09-12",
      "identifiers": {
        "arxiv": "2609.13873"
      },
      "record_updated_at": "2026-09-12"
    },
    "genre": "preprint",
    "id": "arxiv:2609.13873",
    "issued": {
      "date-parts": [
        [
          2026,
          9,
          12
        ]
      ]
    },
    "note": "First published: 2026-09-12; Recorded arXiv version: v1; Recorded version updated: 2026-09-12T10:55:54Z.",
    "title": "PriMobiBench: Characterizing Visual Privacy Leakage in VLM-Driven Mobile GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2609.16732v1",
    "archive": "arXiv",
    "archive_location": "2609.16732",
    "author": [
      {
        "literal": "Heng Li"
      },
      {
        "literal": "Fulin Zhao"
      },
      {
        "literal": "Zhe Geng"
      },
      {
        "literal": "Zhiyuan Yao"
      },
      {
        "literal": "Wei Yuan"
      },
      {
        "literal": "Xiapu Luo"
      }
    ],
    "citation-key": "arxiv_2609_16732",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "b86516b7695d23ffc9179c0829209dc28b96c3c819525eab62a293a68ab5daf0",
        "submitted_at": "2026-09-15T07:02:10Z",
        "updated_at": "2026-09-15T07:02:10Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2609.16732v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2609.16732",
      "catalog_id": "arxiv:2609.16732",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-09-15",
      "identifiers": {
        "arxiv": "2609.16732"
      },
      "record_updated_at": "2026-09-15"
    },
    "genre": "preprint",
    "id": "arxiv:2609.16732",
    "issued": {
      "date-parts": [
        [
          2026,
          9,
          15
        ]
      ]
    },
    "note": "First published: 2026-09-15; Recorded arXiv version: v1; Recorded version updated: 2026-09-15T07:02:10Z.",
    "title": "When Agents See Differently: Exposing UI Desynchronization Threats in Mobile Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2609.18690v1",
    "archive": "arXiv",
    "archive_location": "2609.18690",
    "author": [
      {
        "literal": "Liyang Fan"
      },
      {
        "literal": "Xinping Bi"
      },
      {
        "literal": "Yitai Li"
      },
      {
        "literal": "Shuaimin Li"
      },
      {
        "literal": "Hui Li"
      },
      {
        "literal": "Min Yang"
      }
    ],
    "citation-key": "arxiv_2609_18690",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "ccbc85f4d2598b4cb1e6e1a96b3b9184ddeba838cb610658070fd2d1ac9c8d06",
        "submitted_at": "2026-09-16T14:06:38Z",
        "updated_at": "2026-09-16T14:06:38Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2609.18690v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2609.18690",
      "catalog_id": "arxiv:2609.18690",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-09-16",
      "identifiers": {
        "arxiv": "2609.18690"
      },
      "record_updated_at": "2026-09-16"
    },
    "genre": "preprint",
    "id": "arxiv:2609.18690",
    "issued": {
      "date-parts": [
        [
          2026,
          9,
          16
        ]
      ]
    },
    "note": "First published: 2026-09-16; Recorded arXiv version: v1; Recorded version updated: 2026-09-16T14:06:38Z.",
    "title": "RankGround: Efficient High-Resolution GUI Grounding via Lightweight Reranker-Guided Crop Selection",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2609.27461v1",
    "archive": "arXiv",
    "archive_location": "2609.27461",
    "author": [
      {
        "literal": "Zeyu Zhang"
      },
      {
        "literal": "Dingyi Rong"
      },
      {
        "literal": "Zijian Chen"
      },
      {
        "literal": "Zicheng Zhang"
      },
      {
        "literal": "Xiongkuo Min"
      },
      {
        "literal": "Guangtao Zhai"
      }
    ],
    "citation-key": "arxiv_2609_27461",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "3a89489bb1ff3001a1d806c3eefd8a6aa19503d1dfbe0265b916766119f96ec2",
        "submitted_at": "2026-09-23T07:27:23Z",
        "updated_at": "2026-09-23T07:27:23Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2609.27461v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2609.27461",
      "catalog_id": "arxiv:2609.27461",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-09-23",
      "identifiers": {
        "arxiv": "2609.27461"
      },
      "record_updated_at": "2026-09-23"
    },
    "genre": "preprint",
    "id": "arxiv:2609.27461",
    "issued": {
      "date-parts": [
        [
          2026,
          9,
          23
        ]
      ]
    },
    "note": "First published: 2026-09-23; Recorded arXiv version: v1; Recorded version updated: 2026-09-23T07:27:23Z.",
    "title": "Invisible in Space, Visible in Time: Motion Vision CAPTCHA against GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2609.27770v1",
    "archive": "arXiv",
    "archive_location": "2609.27770",
    "author": [
      {
        "literal": "Zhitong Guo"
      },
      {
        "literal": "Jing Yu Koh"
      },
      {
        "literal": "Ruiyu Li"
      }
    ],
    "citation-key": "arxiv_2609_27770",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "80f6fb973e9f8d62e515d02105d08be774fc32ed5b20a7ecee92b45d112415aa",
        "submitted_at": "2026-08-16T19:54:53Z",
        "updated_at": "2026-08-16T19:54:53Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2609.27770v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2609.27770",
      "catalog_id": "arxiv:2609.27770",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-08-16",
      "identifiers": {
        "arxiv": "2609.27770"
      },
      "record_updated_at": "2026-08-16"
    },
    "genre": "preprint",
    "id": "arxiv:2609.27770",
    "issued": {
      "date-parts": [
        [
          2026,
          8,
          16
        ]
      ]
    },
    "note": "First published: 2026-08-16; Recorded arXiv version: v1; Recorded version updated: 2026-08-16T19:54:53Z.",
    "title": "Improving LLM-based Autonomous Web Agents with Filtering",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2609.31364v1",
    "archive": "arXiv",
    "archive_location": "2609.31364",
    "author": [
      {
        "literal": "Kiana Hooshanfar"
      },
      {
        "literal": "Amirhossein Kazerouni"
      },
      {
        "literal": "Alireza Hosseini"
      },
      {
        "literal": "Michael Brudno"
      },
      {
        "literal": "Babak Taati"
      }
    ],
    "citation-key": "arxiv_2609_31364",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "9ce76f34abe391289643321027a33ac3cac8b5bd64eaa901f9a5fbf7c5561362",
        "submitted_at": "2026-09-25T14:59:14Z",
        "updated_at": "2026-09-25T14:59:14Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2609.31364v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2609.31364",
      "catalog_id": "arxiv:2609.31364",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "adjacent",
      "first_published_at": "2026-09-25",
      "identifiers": {
        "arxiv": "2609.31364"
      },
      "record_updated_at": "2026-09-25"
    },
    "genre": "preprint",
    "id": "arxiv:2609.31364",
    "issued": {
      "date-parts": [
        [
          2026,
          9,
          25
        ]
      ]
    },
    "note": "First published: 2026-09-25; Recorded arXiv version: v1; Recorded version updated: 2026-09-25T14:59:14Z.",
    "title": "OpenVAM: Open-World Visual Attention Modeling with VLMs",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2610.05185v1",
    "archive": "arXiv",
    "archive_location": "2610.05185",
    "author": [
      {
        "literal": "Kaiyu Wu"
      },
      {
        "literal": "Beichen Zheng"
      },
      {
        "literal": "Weiyao Huang"
      },
      {
        "literal": "Keze Wang"
      }
    ],
    "citation-key": "arxiv_2610_05185",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "6d20eb090847d25deb8f69181caa6f964661bbf167223b5572cf3e1cafa52bbd",
        "submitted_at": "2026-10-04T12:49:01Z",
        "updated_at": "2026-10-04T12:49:01Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2610.05185v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2610.05185",
      "catalog_id": "arxiv:2610.05185",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-10-04",
      "identifiers": {
        "arxiv": "2610.05185"
      },
      "record_updated_at": "2026-10-04"
    },
    "genre": "preprint",
    "id": "arxiv:2610.05185",
    "issued": {
      "date-parts": [
        [
          2026,
          10,
          4
        ]
      ]
    },
    "note": "First published: 2026-10-04; Recorded arXiv version: v1; Recorded version updated: 2026-10-04T12:49:01Z.",
    "title": "Recurrent Latent Visual Search for GUI Grounding",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2610.12823v1",
    "archive": "arXiv",
    "archive_location": "2610.12823",
    "author": [
      {
        "literal": "Yisheng Li"
      },
      {
        "literal": "Dongming Han"
      },
      {
        "literal": "Hongkun Pan"
      },
      {
        "literal": "Bingcheng Mao"
      },
      {
        "literal": "Zijian Wang"
      },
      {
        "literal": "Yunlong Mao"
      },
      {
        "literal": "Wei Tong"
      },
      {
        "literal": "Sheng Zhong"
      }
    ],
    "citation-key": "arxiv_2610_12823",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "e6f1521fdfdf6a11a2a195feb05fd915afd6e9bb2332486b870da6375214ac1a",
        "submitted_at": "2026-10-09T00:03:13Z",
        "updated_at": "2026-10-09T00:03:13Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2610.12823v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2610.12823",
      "catalog_id": "arxiv:2610.12823",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-10-09",
      "identifiers": {
        "arxiv": "2610.12823"
      },
      "record_updated_at": "2026-10-09"
    },
    "genre": "preprint",
    "id": "arxiv:2610.12823",
    "issued": {
      "date-parts": [
        [
          2026,
          10,
          9
        ]
      ]
    },
    "note": "First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T00:03:13Z.",
    "title": "When Charts Deceive Web Agents: A Paired Benchmark for Misleading Visualization-Grounded Tasks",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2610.12866v1",
    "archive": "arXiv",
    "archive_location": "2610.12866",
    "author": [
      {
        "literal": "Shangquan Sun"
      },
      {
        "literal": "Ruoyu Chen"
      },
      {
        "literal": "Zhirui Liu"
      },
      {
        "literal": "Xiang Liu"
      },
      {
        "literal": "Chenghao Qian"
      },
      {
        "literal": "Wenqi Ren"
      },
      {
        "literal": "Xiaochun Cao"
      }
    ],
    "citation-key": "arxiv_2610_12866",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "7f7effcf5e101cfcc7e229fe4aab40d07401b1dd98cf5ce3b566fef863a42190",
        "submitted_at": "2026-10-09T01:50:26Z",
        "updated_at": "2026-10-09T01:50:26Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2610.12866v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2610.12866",
      "catalog_id": "arxiv:2610.12866",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-10-09",
      "identifiers": {
        "arxiv": "2610.12866"
      },
      "record_updated_at": "2026-10-09"
    },
    "genre": "preprint",
    "id": "arxiv:2610.12866",
    "issued": {
      "date-parts": [
        [
          2026,
          10,
          9
        ]
      ]
    },
    "note": "First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T01:50:26Z.",
    "title": "CaptchaAgent: Verifiable Visual Reasoning for CAPTCHA Solving",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2610.16234v1",
    "archive": "arXiv",
    "archive_location": "2610.16234",
    "author": [
      {
        "literal": "Jingchao Wang"
      },
      {
        "literal": "Dingjiang Huang"
      }
    ],
    "citation-key": "arxiv_2610_16234",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "aa0e0ab6eb19ea55e65ccb354ae515f6552cd03dd688c6f43cdc6e2d59b11824",
        "submitted_at": "2026-10-12T06:09:02Z",
        "updated_at": "2026-10-12T06:09:02Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2610.16234v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2610.16234",
      "catalog_id": "arxiv:2610.16234",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-10-12",
      "identifiers": {
        "arxiv": "2610.16234"
      },
      "record_updated_at": "2026-10-12"
    },
    "genre": "preprint",
    "id": "arxiv:2610.16234",
    "issued": {
      "date-parts": [
        [
          2026,
          10,
          12
        ]
      ]
    },
    "note": "First published: 2026-10-12; Recorded arXiv version: v1; Recorded version updated: 2026-10-12T06:09:02Z.",
    "title": "Seg2Click: Learning Pixel-Level Action Masks for GUI Visual Grounding",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2610.17792v1",
    "archive": "arXiv",
    "archive_location": "2610.17792",
    "author": [
      {
        "literal": "Minghua Chen"
      },
      {
        "literal": "Xingming Liao"
      },
      {
        "literal": "Weiqiang Zhong"
      },
      {
        "literal": "Zhuowei Wang"
      }
    ],
    "citation-key": "arxiv_2610_17792",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "b1786bba4f48ca54166d49e3d98d55aaef52eb6e2233f282d8d94d54dfb5ed2c",
        "submitted_at": "2026-10-13T06:20:38Z",
        "updated_at": "2026-10-13T06:20:38Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2610.17792v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2610.17792",
      "catalog_id": "arxiv:2610.17792",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-10-13",
      "identifiers": {
        "arxiv": "2610.17792"
      },
      "record_updated_at": "2026-10-13"
    },
    "genre": "preprint",
    "id": "arxiv:2610.17792",
    "issued": {
      "date-parts": [
        [
          2026,
          10,
          13
        ]
      ]
    },
    "note": "First published: 2026-10-13; Recorded arXiv version: v1; Recorded version updated: 2026-10-13T06:20:38Z.",
    "title": "MHVF: Training-Free GUI Grounding via Verification-Guided Multi-Hypothesis Search",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2610.18508v1",
    "archive": "arXiv",
    "archive_location": "2610.18508",
    "author": [
      {
        "literal": "Dominik Seip"
      },
      {
        "literal": "Bartol Markovinović"
      },
      {
        "literal": "Matthias Hein"
      }
    ],
    "citation-key": "arxiv_2610_18508",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "5565d38dd40b02b4158d7edcc2c5c27e7e285dbedefe1c7101a31c4f8d17b659",
        "submitted_at": "2026-10-13T15:03:33Z",
        "updated_at": "2026-10-13T15:03:33Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2610.18508v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2610.18508",
      "catalog_id": "arxiv:2610.18508",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-10-13",
      "identifiers": {
        "arxiv": "2610.18508"
      },
      "record_updated_at": "2026-10-13"
    },
    "genre": "preprint",
    "id": "arxiv:2610.18508",
    "issued": {
      "date-parts": [
        [
          2026,
          10,
          13
        ]
      ]
    },
    "note": "First published: 2026-10-13; Recorded arXiv version: v1; Recorded version updated: 2026-10-13T15:03:33Z.",
    "title": "Towards Safe Autonomy for Computer Use",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2610.20390v1",
    "archive": "arXiv",
    "archive_location": "2610.20390",
    "author": [
      {
        "literal": "Shuo Wang"
      },
      {
        "literal": "Sifan Zhou"
      },
      {
        "literal": "Xiaobo Wang"
      },
      {
        "literal": "Tianyu Fu"
      },
      {
        "literal": "Chenxu Zhao"
      },
      {
        "literal": "Anyang Su"
      },
      {
        "literal": "Hanning Wang"
      },
      {
        "literal": "Ping Jiang"
      },
      {
        "literal": "Minghui Wu"
      }
    ],
    "citation-key": "arxiv_2610_20390",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "1f9d3ce7dffa8c726ce8129083c8d6c580449d1a32d87c7cd3aaade4fe6cf59b",
        "submitted_at": "2026-10-14T15:53:48Z",
        "updated_at": "2026-10-14T15:53:48Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2610.20390v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2610.20390",
      "catalog_id": "arxiv:2610.20390",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-10-14",
      "identifiers": {
        "arxiv": "2610.20390"
      },
      "record_updated_at": "2026-10-14"
    },
    "genre": "preprint",
    "id": "arxiv:2610.20390",
    "issued": {
      "date-parts": [
        [
          2026,
          10,
          14
        ]
      ]
    },
    "note": "First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T15:53:48Z.",
    "title": "STP-GUI: Spatially-Aware Token Pruning for Efficient Web-GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2610.26203v1",
    "archive": "arXiv",
    "archive_location": "2610.26203",
    "author": [
      {
        "literal": "Fuyao Zhang"
      },
      {
        "literal": "Wenwen He"
      },
      {
        "literal": "Jiaming Zhang"
      },
      {
        "literal": "Yurong Hao"
      },
      {
        "literal": "Xuan Wang"
      },
      {
        "literal": "Guowei Guan"
      },
      {
        "literal": "Che Wang"
      },
      {
        "literal": "Longtao Huang"
      },
      {
        "literal": "Wei Yang Bryan Lim"
      }
    ],
    "citation-key": "arxiv_2610_26203",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "41178d19a23653c0f49423b8f725584bded7ab8819a1a46e83a062794460b4cb",
        "submitted_at": "2026-10-19T11:30:48Z",
        "updated_at": "2026-10-19T11:30:48Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2610.26203v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2610.26203",
      "catalog_id": "arxiv:2610.26203",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-10-19",
      "identifiers": {
        "arxiv": "2610.26203"
      },
      "record_updated_at": "2026-10-19"
    },
    "genre": "preprint",
    "id": "arxiv:2610.26203",
    "issued": {
      "date-parts": [
        [
          2026,
          10,
          19
        ]
      ]
    },
    "note": "First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T11:30:48Z.",
    "title": "Focused Omni-Modal GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "DOI": "10.1145/1622176.1622213",
    "URL": "https://doi.org/10.1145/1622176.1622213",
    "author": [
      {
        "literal": "Tom Yeh"
      },
      {
        "literal": "Tsung-Hsiang Chang"
      },
      {
        "literal": "Robert C. Miller"
      }
    ],
    "citation-key": "cua_510831381c08385eb74fb95e",
    "container-title": "Proceedings of the 22nd Annual ACM Symposium on User Interface Software and Technology (UIST '09)",
    "custom": {
      "canonical_source_url": "https://doi.org/10.1145/1622176.1622213",
      "catalog_id": "url:a4cdb2ee0d07d3980651",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "citation_edition": "publication",
      "first_published_at": null,
      "identifiers": {
        "doi": "10.1145/1622176.1622213"
      },
      "publication": {
        "authors": [
          "Tom Yeh",
          "Tsung-Hsiang Chang",
          "Robert C. Miller"
        ],
        "date_basis": "Supplied month precision: 2009-10. Date Issued: October 2009",
        "date_parts": [
          2009,
          10
        ],
        "doi": "10.1145/1622176.1622213",
        "event_dates": null,
        "evidence_urls": [
          "https://dspace.mit.edu/entities/publication/604a3f79-451d-4186-a94e-d12690ffe40a"
        ],
        "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.",
        "issue": null,
        "notes": "Institutional abstract and published-version citation supply the retained evidence; the institution identifies an author final manuscript record. Exact publication day is not supplied. Operating-system-specific experiments are not asserted.",
        "pages": "183-192",
        "pdf_url": null,
        "publisher": null,
        "series": null,
        "title": "Sikuli: Using GUI screenshots for search and automation",
        "type": "conference-paper",
        "url": "https://doi.org/10.1145/1622176.1622213",
        "venue": "Proceedings of the 22nd Annual ACM Symposium on User Interface Software and Technology (UIST '09)",
        "volume": null
      },
      "record_updated_at": null
    },
    "id": "url:a4cdb2ee0d07d3980651",
    "issued": {
      "date-parts": [
        [
          2009,
          10
        ]
      ]
    },
    "note": "Publication date: 2009-10.",
    "page": "183-192",
    "title": "Sikuli: Using GUI screenshots for search and automation",
    "type": "paper-conference"
  },
  {
    "DOI": "10.1145/3126594.3126651",
    "URL": "https://doi.org/10.1145/3126594.3126651",
    "author": [
      {
        "literal": "Biplab Deka"
      },
      {
        "literal": "Zifeng Huang"
      },
      {
        "literal": "Chad Franzen"
      },
      {
        "literal": "Joshua Hibschman"
      },
      {
        "literal": "Daniel Afergan"
      },
      {
        "literal": "Yang Li"
      },
      {
        "literal": "Jeffrey Nichols"
      },
      {
        "literal": "Ranjitha Kumar"
      }
    ],
    "citation-key": "cua_402ed654426712089390317c",
    "container-title": "UIST '17: Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology",
    "custom": {
      "canonical_source_url": "https://doi.org/10.1145/3126594.3126651",
      "catalog_id": "url:b560b5d6abaab98483f6",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "citation_edition": "publication",
      "first_published_at": "2017-10-20",
      "identifiers": {
        "doi": "10.1145/3126594.3126651"
      },
      "publication": {
        "authors": [
          "Biplab Deka",
          "Zifeng Huang",
          "Chad Franzen",
          "Joshua Hibschman",
          "Daniel Afergan",
          "Yang Li",
          "Jeffrey Nichols",
          "Ranjitha Kumar"
        ],
        "date_basis": "Supplied day precision: 2017-10-20. PDF cover, Published: 20 October 2017 The 18 January 2026 download date and October 22-25 conference dates are not publication dates.",
        "date_parts": [
          2017,
          10,
          20
        ],
        "doi": "10.1145/3126594.3126651",
        "event_dates": null,
        "evidence_urls": [
          "https://danafergan.com/publications/deka2017rico.pdf",
          "https://dev.interactionmining.org/archive/rico"
        ],
        "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.",
        "issue": null,
        "notes": "The paper is a distinct resource from the already cataloged Rico dataset (url:0b134b082a7bd507fc6a). The publisher PDF describes 9.7k apps and 72k screens; the project page describes 9.3k apps and 66k screens. The annotation intentionally supplies no merged size claim. No volume number is supplied for this proceedings article.",
        "pages": "845-854",
        "pdf_url": "https://danafergan.com/publications/deka2017rico.pdf",
        "publisher": null,
        "series": null,
        "title": "Rico: A Mobile App Dataset for Building Data-Driven Design Applications",
        "type": "conference-paper",
        "url": "https://doi.org/10.1145/3126594.3126651",
        "venue": "UIST '17: Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology",
        "volume": null
      },
      "record_updated_at": null
    },
    "id": "url:b560b5d6abaab98483f6",
    "issued": {
      "date-parts": [
        [
          2017,
          10,
          20
        ]
      ]
    },
    "note": "Publication date: 2017-10-20.",
    "page": "845-854",
    "title": "Rico: A Mobile App Dataset for Building Data-Driven Design Applications",
    "type": "paper-conference"
  }
]