[
  {
    "URL": "https://arxiv.org/abs/2307.13854v4",
    "archive": "arXiv",
    "archive_location": "2307.13854",
    "author": [
      {
        "literal": "Shuyan Zhou"
      },
      {
        "literal": "Frank F. Xu"
      },
      {
        "literal": "Hao Zhu"
      },
      {
        "literal": "Xuhui Zhou"
      },
      {
        "literal": "Robert Lo"
      },
      {
        "literal": "Abishek Sridhar"
      },
      {
        "literal": "Xianyi Cheng"
      },
      {
        "literal": "Tianyue Ou"
      },
      {
        "literal": "Yonatan Bisk"
      },
      {
        "literal": "Daniel Fried"
      },
      {
        "literal": "Uri Alon"
      },
      {
        "literal": "Graham Neubig"
      }
    ],
    "citation-key": "arxiv_2307_13854",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "0e9eca0165573ba53b663acbb1c7962fd2d64bc6633f10397f9cad229772a363",
        "submitted_at": "2023-07-25T22:59:32Z",
        "updated_at": "2024-04-16T15:13:18Z",
        "version": 4,
        "versioned_url": "https://arxiv.org/abs/2307.13854v4"
      },
      "canonical_source_url": "https://arxiv.org/abs/2307.13854",
      "catalog_id": "arxiv:2307.13854",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2023-07-25",
      "identifiers": {
        "arxiv": "2307.13854"
      },
      "record_updated_at": "2024-04-16"
    },
    "genre": "preprint",
    "id": "arxiv:2307.13854",
    "issued": {
      "date-parts": [
        [
          2023,
          7,
          25
        ]
      ]
    },
    "note": "First published: 2023-07-25; Recorded arXiv version: v4; Recorded version updated: 2024-04-16T15:13:18Z.",
    "title": "WebArena: A Realistic Web Environment for Building Autonomous Agents",
    "type": "article",
    "version": "4"
  },
  {
    "URL": "https://arxiv.org/abs/2311.18751v3",
    "archive": "arXiv",
    "archive_location": "2311.18751",
    "author": [
      {
        "literal": "Hiroki Furuta"
      },
      {
        "literal": "Yutaka Matsuo"
      },
      {
        "literal": "Aleksandra Faust"
      },
      {
        "literal": "Izzeddin Gur"
      }
    ],
    "citation-key": "arxiv_2311_18751",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "4b00e0a9c74b7ac8819bdda540a1069c33cbac45f0c7fb853dee995f2feb9a59",
        "submitted_at": "2023-11-30T17:50:47Z",
        "updated_at": "2024-12-31T04:24:16Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2311.18751v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2311.18751",
      "catalog_id": "arxiv:2311.18751",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2023-11-30",
      "identifiers": {
        "arxiv": "2311.18751"
      },
      "record_updated_at": "2024-12-31"
    },
    "genre": "preprint",
    "id": "arxiv:2311.18751",
    "issued": {
      "date-parts": [
        [
          2023,
          11,
          30
        ]
      ]
    },
    "note": "First published: 2023-11-30; Recorded arXiv version: v3; Recorded version updated: 2024-12-31T04:24:16Z.",
    "title": "Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2404.09992v2",
    "archive": "arXiv",
    "archive_location": "2404.09992",
    "author": [
      {
        "literal": "Shulin Tian"
      },
      {
        "literal": "Ziniu Zhang"
      },
      {
        "literal": "Liangyu Chen"
      },
      {
        "literal": "Ziwei Liu"
      }
    ],
    "citation-key": "arxiv_2404_09992",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "667b1f5053f3ae6ea712999932d5e9ee2f42e402cc72e713048d0790f5931976",
        "submitted_at": "2024-04-15T17:59:50Z",
        "updated_at": "2025-06-29T05:24:54Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2404.09992v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2404.09992",
      "catalog_id": "arxiv:2404.09992",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "citation_edition": "record",
      "first_published_at": "2024-04-15",
      "identifiers": {
        "arxiv": "2404.09992"
      },
      "publication": {
        "authors": [
          "Shulin Tian",
          "Ziniu Zhang",
          "Liang-Yu Chen",
          "Ziwei Liu"
        ],
        "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.703",
        "event_dates": null,
        "evidence_urls": [
          "https://aclanthology.org/2025.findings-acl.703/"
        ],
        "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": "13682-13697",
        "pdf_url": "https://aclanthology.org/2025.findings-acl.703.pdf",
        "publisher": "Association for Computational Linguistics",
        "series": null,
        "title": "MMInA: Benchmarking Multihop Multimodal Internet Agents",
        "type": "conference-paper",
        "url": "https://aclanthology.org/2025.findings-acl.703/",
        "venue": "Findings of the Association for Computational Linguistics: ACL 2025",
        "volume": null
      },
      "record_updated_at": "2025-06-29"
    },
    "genre": "preprint",
    "id": "arxiv:2404.09992",
    "issued": {
      "date-parts": [
        [
          2024,
          4,
          15
        ]
      ]
    },
    "note": "First published: 2024-04-15; Recorded arXiv version: v2; Recorded version updated: 2025-06-29T05:24:54Z.",
    "title": "MMInA: Benchmarking Multihop Multimodal Internet Agents",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2407.19056v1",
    "archive": "arXiv",
    "archive_location": "2407.19056",
    "author": [
      {
        "literal": "Zilong Wang"
      },
      {
        "literal": "Yuedong Cui"
      },
      {
        "literal": "Li Zhong"
      },
      {
        "literal": "Zimin Zhang"
      },
      {
        "literal": "Da Yin"
      },
      {
        "literal": "Bill Yuchen Lin"
      },
      {
        "literal": "Jingbo Shang"
      }
    ],
    "citation-key": "arxiv_2407_19056",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "c443e6a508c438332ac5990cf254a4441f5bdcc24354fd8aeca36bcbf4604a29",
        "submitted_at": "2024-07-26T19:27:17Z",
        "updated_at": "2024-07-26T19:27:17Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2407.19056v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2407.19056",
      "catalog_id": "arxiv:2407.19056",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-07-26",
      "identifiers": {
        "arxiv": "2407.19056"
      },
      "record_updated_at": "2024-07-26"
    },
    "genre": "preprint",
    "id": "arxiv:2407.19056",
    "issued": {
      "date-parts": [
        [
          2024,
          7,
          26
        ]
      ]
    },
    "note": "First published: 2024-07-26; Recorded arXiv version: v1; Recorded version updated: 2024-07-26T19:27:17Z.",
    "title": "OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2408.15978v1",
    "archive": "arXiv",
    "archive_location": "2408.15978",
    "author": [
      {
        "literal": "Yao Zhang"
      },
      {
        "literal": "Zijian Ma"
      },
      {
        "literal": "Yunpu Ma"
      },
      {
        "literal": "Zhen Han"
      },
      {
        "literal": "Yu Wu"
      },
      {
        "literal": "Volker Tresp"
      }
    ],
    "citation-key": "arxiv_2408_15978",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "9e3a34f16101df7a96ffdabbdf86b060e195494f16499f20bdf54110a0394cae",
        "submitted_at": "2024-08-28T17:49:29Z",
        "updated_at": "2024-08-28T17:49:29Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2408.15978v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2408.15978",
      "catalog_id": "arxiv:2408.15978",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-08-28",
      "identifiers": {
        "arxiv": "2408.15978"
      },
      "record_updated_at": "2024-08-28"
    },
    "genre": "preprint",
    "id": "arxiv:2408.15978",
    "issued": {
      "date-parts": [
        [
          2024,
          8,
          28
        ]
      ]
    },
    "note": "First published: 2024-08-28; Recorded arXiv version: v1; Recorded version updated: 2024-08-28T17:49:29Z.",
    "title": "WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2412.14161v3",
    "archive": "arXiv",
    "archive_location": "2412.14161",
    "author": [
      {
        "literal": "Frank F. Xu"
      },
      {
        "literal": "Yufan Song"
      },
      {
        "literal": "Boxuan Li"
      },
      {
        "literal": "Yuxuan Tang"
      },
      {
        "literal": "Kritanjali Jain"
      },
      {
        "literal": "Mengxue Bao"
      },
      {
        "literal": "Zora Z. Wang"
      },
      {
        "literal": "Xuhui Zhou"
      },
      {
        "literal": "Zhitong Guo"
      },
      {
        "literal": "Murong Cao"
      },
      {
        "literal": "Mingyang Yang"
      },
      {
        "literal": "Hao Yang Lu"
      },
      {
        "literal": "Amaad Martin"
      },
      {
        "literal": "Zhe Su"
      },
      {
        "literal": "Leander Maben"
      },
      {
        "literal": "Raj Mehta"
      },
      {
        "literal": "Wayne Chi"
      },
      {
        "literal": "Lawrence Jang"
      },
      {
        "literal": "Yiqing Xie"
      },
      {
        "literal": "Shuyan Zhou"
      },
      {
        "literal": "Graham Neubig"
      }
    ],
    "citation-key": "arxiv_2412_14161",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "77f91dd9ec9f50fb5526a78cfe270a7a1705d5bd83a2aef26644453740c005d5",
        "submitted_at": "2024-12-18T18:55:40Z",
        "updated_at": "2025-09-10T08:35:19Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2412.14161v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2412.14161",
      "catalog_id": "arxiv:2412.14161",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2024-12-18",
      "identifiers": {
        "arxiv": "2412.14161"
      },
      "record_updated_at": "2025-09-10"
    },
    "genre": "preprint",
    "id": "arxiv:2412.14161",
    "issued": {
      "date-parts": [
        [
          2024,
          12,
          18
        ]
      ]
    },
    "note": "First published: 2024-12-18; Recorded arXiv version: v3; Recorded version updated: 2025-09-10T08:35:19Z.",
    "title": "TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2501.11733v2",
    "archive": "arXiv",
    "archive_location": "2501.11733",
    "author": [
      {
        "literal": "Zhenhailong Wang"
      },
      {
        "literal": "Haiyang Xu"
      },
      {
        "literal": "Junyang Wang"
      },
      {
        "literal": "Xi Zhang"
      },
      {
        "literal": "Ming Yan"
      },
      {
        "literal": "Ji Zhang"
      },
      {
        "literal": "Fei Huang"
      },
      {
        "literal": "Heng Ji"
      }
    ],
    "citation-key": "arxiv_2501_11733",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "5cf28f084cac7fc38e5c2dc4654115356d2d57f16009aad8925e071b8005be9c",
        "submitted_at": "2025-01-20T20:35:46Z",
        "updated_at": "2025-01-28T16:58:02Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2501.11733v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2501.11733",
      "catalog_id": "arxiv:2501.11733",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-01-20",
      "identifiers": {
        "arxiv": "2501.11733"
      },
      "record_updated_at": "2025-01-28"
    },
    "genre": "preprint",
    "id": "arxiv:2501.11733",
    "issued": {
      "date-parts": [
        [
          2025,
          1,
          20
        ]
      ]
    },
    "note": "First published: 2025-01-20; Recorded arXiv version: v2; Recorded version updated: 2025-01-28T16:58:02Z.",
    "title": "Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2503.09572v3",
    "archive": "arXiv",
    "archive_location": "2503.09572",
    "author": [
      {
        "literal": "Lutfi Eren Erdogan"
      },
      {
        "literal": "Nicholas Lee"
      },
      {
        "literal": "Sehoon Kim"
      },
      {
        "literal": "Suhong Moon"
      },
      {
        "literal": "Hiroki Furuta"
      },
      {
        "literal": "Gopala Anumanchipalli"
      },
      {
        "literal": "Kurt Keutzer"
      },
      {
        "literal": "Amir Gholami"
      }
    ],
    "citation-key": "arxiv_2503_09572",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "6b03d84f29bb524d7950039624e0d460d8381f2ba63d70c69f5f958013730db9",
        "submitted_at": "2025-03-12T17:40:52Z",
        "updated_at": "2025-04-22T17:56:22Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2503.09572v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2503.09572",
      "catalog_id": "arxiv:2503.09572",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-03-12",
      "identifiers": {
        "arxiv": "2503.09572"
      },
      "record_updated_at": "2025-04-22"
    },
    "genre": "preprint",
    "id": "arxiv:2503.09572",
    "issued": {
      "date-parts": [
        [
          2025,
          3,
          12
        ]
      ]
    },
    "note": "First published: 2025-03-12; Recorded arXiv version: v3; Recorded version updated: 2025-04-22T17:56:22Z.",
    "title": "Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2504.10445v2",
    "archive": "arXiv",
    "archive_location": "2504.10445",
    "author": [
      {
        "literal": "Suyu Ye"
      },
      {
        "literal": "Haojun Shi"
      },
      {
        "literal": "Darren Shih"
      },
      {
        "literal": "Hyokun Yun"
      },
      {
        "literal": "Tanya Roosta"
      },
      {
        "literal": "Tianmin Shu"
      }
    ],
    "citation-key": "arxiv_2504_10445",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "268adf347e1f224f434e6dba838873c99a4050686cae1495643d9638d840d809",
        "submitted_at": "2025-04-14T17:36:46Z",
        "updated_at": "2025-12-01T15:22:40Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2504.10445v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2504.10445",
      "catalog_id": "arxiv:2504.10445",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-04-14",
      "identifiers": {
        "arxiv": "2504.10445"
      },
      "record_updated_at": "2025-12-01"
    },
    "genre": "preprint",
    "id": "arxiv:2504.10445",
    "issued": {
      "date-parts": [
        [
          2025,
          4,
          14
        ]
      ]
    },
    "note": "First published: 2025-04-14; Recorded arXiv version: v2; Recorded version updated: 2025-12-01T15:22:40Z.",
    "title": "RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2505.03570v1",
    "archive": "arXiv",
    "archive_location": "2505.03570",
    "author": [
      {
        "literal": "Mariya Davydova"
      },
      {
        "literal": "Daniel Jeffries"
      },
      {
        "literal": "Patrick Barker"
      },
      {
        "literal": "Arturo Márquez Flores"
      },
      {
        "literal": "Sinéad Ryan"
      }
    ],
    "citation-key": "arxiv_2505_03570",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "e8bb4c6f8080ed1ee91e1089233cae6f231ab3256b38ac7d6403ebea3ae56fe0",
        "submitted_at": "2025-05-06T14:29:47Z",
        "updated_at": "2025-05-06T14:29:47Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2505.03570v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2505.03570",
      "catalog_id": "arxiv:2505.03570",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-05-06",
      "identifiers": {
        "arxiv": "2505.03570"
      },
      "record_updated_at": "2025-05-06"
    },
    "genre": "preprint",
    "id": "arxiv:2505.03570",
    "issued": {
      "date-parts": [
        [
          2025,
          5,
          6
        ]
      ]
    },
    "note": "First published: 2025-05-06; Recorded arXiv version: v1; Recorded version updated: 2025-05-06T14:29:47Z.",
    "title": "OSUniverse: Benchmark for Multimodal GUI-navigation AI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2505.16282v1",
    "archive": "arXiv",
    "archive_location": "2505.16282",
    "author": [
      {
        "literal": "Fanbin Lu"
      },
      {
        "literal": "Zhisheng Zhong"
      },
      {
        "literal": "Shu Liu"
      },
      {
        "literal": "Chi-Wing Fu"
      },
      {
        "literal": "Jiaya Jia"
      }
    ],
    "citation-key": "arxiv_2505_16282",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "c092569d4d79026ddbdcc3bc9da1cfc617ff44886dab0b36f311cc81083e0fb5",
        "submitted_at": "2025-05-22T06:24:32Z",
        "updated_at": "2025-05-22T06:24:32Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2505.16282v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2505.16282",
      "catalog_id": "arxiv:2505.16282",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-05-22",
      "identifiers": {
        "arxiv": "2505.16282"
      },
      "record_updated_at": "2025-05-22"
    },
    "genre": "preprint",
    "id": "arxiv:2505.16282",
    "issued": {
      "date-parts": [
        [
          2025,
          5,
          22
        ]
      ]
    },
    "note": "First published: 2025-05-22; Recorded arXiv version: v1; Recorded version updated: 2025-05-22T06:24:32Z.",
    "title": "ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2505.24838v2",
    "archive": "arXiv",
    "archive_location": "2505.24838",
    "author": [
      {
        "literal": "Brandon Man"
      },
      {
        "literal": "Ghadi Nehme"
      },
      {
        "literal": "Md Ferdous Alam"
      },
      {
        "literal": "Faez Ahmed"
      }
    ],
    "citation-key": "arxiv_2505_24838",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "f913b87f07fdad0e4c45264c58c8d9b9d13ca26695306d9e0644eb856f18ced7",
        "submitted_at": "2025-05-30T17:39:52Z",
        "updated_at": "2025-11-08T18:27:03Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2505.24838v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2505.24838",
      "catalog_id": "arxiv:2505.24838",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-05-30",
      "identifiers": {
        "arxiv": "2505.24838"
      },
      "record_updated_at": "2025-11-08"
    },
    "genre": "preprint",
    "id": "arxiv:2505.24838",
    "issued": {
      "date-parts": [
        [
          2025,
          5,
          30
        ]
      ]
    },
    "note": "First published: 2025-05-30; Recorded arXiv version: v2; Recorded version updated: 2025-11-08T18:27:03Z.",
    "title": "VideoCAD: A Dataset and Model for Learning Long-Horizon 3D CAD UI Interactions from Video",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2506.07976v2",
    "archive": "arXiv",
    "archive_location": "2506.07976",
    "author": [
      {
        "literal": "Junhong Shen"
      },
      {
        "literal": "Hao Bai"
      },
      {
        "literal": "Lunjun Zhang"
      },
      {
        "literal": "Yifei Zhou"
      },
      {
        "literal": "Amrith Setlur"
      },
      {
        "literal": "Shengbang Tong"
      },
      {
        "literal": "Diego Caples"
      },
      {
        "literal": "Nan Jiang"
      },
      {
        "literal": "Tong Zhang"
      },
      {
        "literal": "Ameet Talwalkar"
      },
      {
        "literal": "Aviral Kumar"
      }
    ],
    "citation-key": "arxiv_2506_07976",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "e4b6c8b297e88dae689ba2a48724a441698cd5309a3bbe1198f38343e88aceb1",
        "submitted_at": "2025-06-09T17:50:02Z",
        "updated_at": "2025-06-10T12:50:18Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2506.07976v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2506.07976",
      "catalog_id": "arxiv:2506.07976",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-06-09",
      "identifiers": {
        "arxiv": "2506.07976"
      },
      "record_updated_at": "2025-06-10"
    },
    "genre": "preprint",
    "id": "arxiv:2506.07976",
    "issued": {
      "date-parts": [
        [
          2025,
          6,
          9
        ]
      ]
    },
    "note": "First published: 2025-06-09; Recorded arXiv version: v2; Recorded version updated: 2025-06-10T12:50:18Z.",
    "title": "Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2506.08972v1",
    "archive": "arXiv",
    "archive_location": "2506.08972",
    "author": [
      {
        "literal": "Yuan Guo"
      },
      {
        "literal": "Tingjia Miao"
      },
      {
        "literal": "Zheng Wu"
      },
      {
        "literal": "Pengzhou Cheng"
      },
      {
        "literal": "Ming Zhou"
      },
      {
        "literal": "Zhuosheng Zhang"
      }
    ],
    "citation-key": "arxiv_2506_08972",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "8dbc84aa582b94775d490cf84e17eff05be84af7dbcc2de7de61b886fa3c9178",
        "submitted_at": "2025-06-10T16:45:29Z",
        "updated_at": "2025-06-10T16:45:29Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2506.08972v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2506.08972",
      "catalog_id": "arxiv:2506.08972",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-06-10",
      "identifiers": {
        "arxiv": "2506.08972"
      },
      "record_updated_at": "2025-06-10"
    },
    "genre": "preprint",
    "id": "arxiv:2506.08972",
    "issued": {
      "date-parts": [
        [
          2025,
          6,
          10
        ]
      ]
    },
    "note": "First published: 2025-06-10; Recorded arXiv version: v1; Recorded version updated: 2025-06-10T16:45:29Z.",
    "title": "Atomic-to-Compositional Generalization for Mobile Agents with A New Benchmark and Scheduling System",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2506.10387v1",
    "archive": "arXiv",
    "archive_location": "2506.10387",
    "author": [
      {
        "literal": "Yuquan Xie"
      },
      {
        "literal": "Zaijing Li"
      },
      {
        "literal": "Rui Shao"
      },
      {
        "literal": "Gongwei Chen"
      },
      {
        "literal": "Kaiwen Zhou"
      },
      {
        "literal": "Yinchuan Li"
      },
      {
        "literal": "Dongmei Jiang"
      },
      {
        "literal": "Liqiang Nie"
      }
    ],
    "citation-key": "arxiv_2506_10387",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "9b353606ce29a5bc60d263e86827a825af46883e25da5bd290b48affa9dd3838",
        "submitted_at": "2025-06-12T06:21:19Z",
        "updated_at": "2025-06-12T06:21:19Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2506.10387v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2506.10387",
      "catalog_id": "arxiv:2506.10387",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-06-12",
      "identifiers": {
        "arxiv": "2506.10387"
      },
      "record_updated_at": "2025-06-12"
    },
    "genre": "preprint",
    "id": "arxiv:2506.10387",
    "issued": {
      "date-parts": [
        [
          2025,
          6,
          12
        ]
      ]
    },
    "note": "First published: 2025-06-12; Recorded arXiv version: v1; Recorded version updated: 2025-06-12T06:21:19Z.",
    "title": "Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2506.14205v2",
    "archive": "arXiv",
    "archive_location": "2506.14205",
    "author": [
      {
        "literal": "Jingxu Xie"
      },
      {
        "literal": "Dylan Xu"
      },
      {
        "literal": "Xuandong Zhao"
      },
      {
        "literal": "Dawn Song"
      }
    ],
    "citation-key": "arxiv_2506_14205",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "ae36b271f9b4799093831cabee772845edfaeca97107414e424e170ccf89904d",
        "submitted_at": "2025-06-17T05:46:52Z",
        "updated_at": "2026-03-02T00:51:36Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2506.14205v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2506.14205",
      "catalog_id": "arxiv:2506.14205",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-06-17",
      "identifiers": {
        "arxiv": "2506.14205"
      },
      "record_updated_at": "2026-03-02"
    },
    "genre": "preprint",
    "id": "arxiv:2506.14205",
    "issued": {
      "date-parts": [
        [
          2025,
          6,
          17
        ]
      ]
    },
    "note": "First published: 2025-06-17; Recorded arXiv version: v2; Recorded version updated: 2026-03-02T00:51:36Z.",
    "title": "AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2507.16853v1",
    "archive": "arXiv",
    "archive_location": "2507.16853",
    "author": [
      {
        "literal": "Ning Li"
      },
      {
        "literal": "Xiangmou Qu"
      },
      {
        "literal": "Jiamu Zhou"
      },
      {
        "literal": "Jun Wang"
      },
      {
        "literal": "Muning Wen"
      },
      {
        "literal": "Kounianhua Du"
      },
      {
        "literal": "Xingyu Lou"
      },
      {
        "literal": "Qiuying Peng"
      },
      {
        "literal": "Jun Wang"
      },
      {
        "literal": "Weinan Zhang"
      }
    ],
    "citation-key": "arxiv_2507_16853",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "6d58a188742fef5862b299c1dcf17bb6be139e81aafd3d2e1bdbe26f88001384",
        "submitted_at": "2025-07-21T09:37:05Z",
        "updated_at": "2025-07-21T09:37:05Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2507.16853v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2507.16853",
      "catalog_id": "arxiv:2507.16853",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-07-21",
      "identifiers": {
        "arxiv": "2507.16853"
      },
      "record_updated_at": "2025-07-21"
    },
    "genre": "preprint",
    "id": "arxiv:2507.16853",
    "issued": {
      "date-parts": [
        [
          2025,
          7,
          21
        ]
      ]
    },
    "note": "First published: 2025-07-21; Recorded arXiv version: v1; Recorded version updated: 2025-07-21T09:37:05Z.",
    "title": "MobileUse: A GUI Agent with Hierarchical Reflection for Autonomous Mobile Operation",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2508.01330v4",
    "archive": "arXiv",
    "archive_location": "2508.01330",
    "author": [
      {
        "literal": "Zihan Zheng"
      },
      {
        "literal": "Tianle Cui"
      },
      {
        "literal": "Taoran Wang"
      },
      {
        "literal": "Fengtao Wang"
      },
      {
        "literal": "Jiahui Pan"
      },
      {
        "literal": "Lewei He"
      },
      {
        "literal": "Qianglong Chen"
      }
    ],
    "citation-key": "arxiv_2508_01330",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "57d89909534af90cbc10b97a992238bde3ae976ac6cc97778b4345635cef552c",
        "submitted_at": "2025-08-02T11:53:41Z",
        "updated_at": "2026-04-20T02:44:32Z",
        "version": 4,
        "versioned_url": "https://arxiv.org/abs/2508.01330v4"
      },
      "canonical_source_url": "https://arxiv.org/abs/2508.01330",
      "catalog_id": "arxiv:2508.01330",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-08-02",
      "identifiers": {
        "arxiv": "2508.01330"
      },
      "record_updated_at": "2026-04-20"
    },
    "genre": "preprint",
    "id": "arxiv:2508.01330",
    "issued": {
      "date-parts": [
        [
          2025,
          8,
          2
        ]
      ]
    },
    "note": "First published: 2025-08-02; Recorded arXiv version: v4; Recorded version updated: 2026-04-20T02:44:32Z.",
    "title": "NaturalGAIA: A Verifiable Benchmark and Hierarchical Framework for Long-Horizon GUI Tasks",
    "type": "article",
    "version": "4"
  },
  {
    "URL": "https://arxiv.org/abs/2509.01052v2",
    "archive": "arXiv",
    "archive_location": "2509.01052",
    "author": [
      {
        "literal": "Jaewoo Ahn"
      },
      {
        "literal": "Junseo Kim"
      },
      {
        "literal": "Heeseung Yun"
      },
      {
        "literal": "Jaehyeon Son"
      },
      {
        "literal": "Dongmin Park"
      },
      {
        "literal": "Jaewoong Cho"
      },
      {
        "literal": "Gunhee Kim"
      }
    ],
    "citation-key": "arxiv_2509_01052",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "3bf86652aaeb252972f3010be38b75b78dfaa9a8063c480c80d0cea47397c2e7",
        "submitted_at": "2025-09-01T01:33:16Z",
        "updated_at": "2025-10-15T10:33:27Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2509.01052v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2509.01052",
      "catalog_id": "arxiv:2509.01052",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "adjacent",
      "first_published_at": "2025-09-01",
      "identifiers": {
        "arxiv": "2509.01052"
      },
      "record_updated_at": "2025-10-15"
    },
    "genre": "preprint",
    "id": "arxiv:2509.01052",
    "issued": {
      "date-parts": [
        [
          2025,
          9,
          1
        ]
      ]
    },
    "note": "First published: 2025-09-01; Recorded arXiv version: v2; Recorded version updated: 2025-10-15T10:33:27Z.",
    "title": "FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2509.02444v2",
    "archive": "arXiv",
    "archive_location": "2509.02444",
    "author": [
      {
        "literal": "Jingru Fan"
      },
      {
        "literal": "Yufan Dang"
      },
      {
        "literal": "Jingyao Wu"
      },
      {
        "literal": "Huatao Li"
      },
      {
        "literal": "Runde Yang"
      },
      {
        "literal": "Xiyuan Yang"
      },
      {
        "literal": "Yuheng Wang"
      },
      {
        "literal": "Chen Qian"
      }
    ],
    "citation-key": "arxiv_2509_02444",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "49a887b12b3395821aa100a66e61aac808309ef947ae752475df3d2db9a4fcd8",
        "submitted_at": "2025-09-02T15:48:21Z",
        "updated_at": "2025-10-17T00:57:58Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2509.02444v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2509.02444",
      "catalog_id": "arxiv:2509.02444",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-09-02",
      "identifiers": {
        "arxiv": "2509.02444"
      },
      "record_updated_at": "2025-10-17"
    },
    "genre": "preprint",
    "id": "arxiv:2509.02444",
    "issued": {
      "date-parts": [
        [
          2025,
          9,
          2
        ]
      ]
    },
    "note": "First published: 2025-09-02; Recorded arXiv version: v2; Recorded version updated: 2025-10-17T00:57:58Z.",
    "title": "AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2509.03891v1",
    "archive": "arXiv",
    "archive_location": "2509.03891",
    "author": [
      {
        "literal": "Gowen Loo"
      },
      {
        "literal": "Chang Liu"
      },
      {
        "literal": "Qinghong Yin"
      },
      {
        "literal": "Xiang Chen"
      },
      {
        "literal": "Jiawei Chen"
      },
      {
        "literal": "Jingyuan Zhang"
      },
      {
        "literal": "Yu Tian"
      }
    ],
    "citation-key": "arxiv_2509_03891",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "a8b2db00f62afe350e55e2266b3627de9b0cf089178b0cf80eb13b06275eee15",
        "submitted_at": "2025-09-04T05:22:42Z",
        "updated_at": "2025-09-04T05:22:42Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2509.03891v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2509.03891",
      "catalog_id": "arxiv:2509.03891",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-09-04",
      "identifiers": {
        "arxiv": "2509.03891"
      },
      "record_updated_at": "2025-09-04"
    },
    "genre": "preprint",
    "id": "arxiv:2509.03891",
    "issued": {
      "date-parts": [
        [
          2025,
          9,
          4
        ]
      ]
    },
    "note": "First published: 2025-09-04; Recorded arXiv version: v1; Recorded version updated: 2025-09-04T05:22:42Z.",
    "title": "MobileRAG: Enhancing Mobile Agent with Retrieval-Augmented Generation",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2509.15738v1",
    "archive": "arXiv",
    "archive_location": "2509.15738",
    "author": [
      {
        "literal": "Musen Lin"
      },
      {
        "literal": "Minghao Liu"
      },
      {
        "literal": "Taoran Lu"
      },
      {
        "literal": "Lichen Yuan"
      },
      {
        "literal": "Yiwei Liu"
      },
      {
        "literal": "Haonan Xu"
      },
      {
        "literal": "Yu Miao"
      },
      {
        "literal": "Yuhao Chao"
      },
      {
        "literal": "Zhaojian Li"
      }
    ],
    "citation-key": "arxiv_2509_15738",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "035048459d2b303721ef0738212829d1fa3314ccd0736b6649cc786c6e975ad4",
        "submitted_at": "2025-09-19T08:09:18Z",
        "updated_at": "2025-09-19T08:09:18Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2509.15738v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2509.15738",
      "catalog_id": "arxiv:2509.15738",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-09-19",
      "identifiers": {
        "arxiv": "2509.15738"
      },
      "record_updated_at": "2025-09-19"
    },
    "genre": "preprint",
    "id": "arxiv:2509.15738",
    "issued": {
      "date-parts": [
        [
          2025,
          9,
          19
        ]
      ]
    },
    "note": "First published: 2025-09-19; Recorded arXiv version: v1; Recorded version updated: 2025-09-19T08:09:18Z.",
    "title": "GUI-ReWalk: Massive Data Generation for GUI Agent via Stochastic Exploration and Intent-Aware Reasoning",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2510.02250v2",
    "archive": "arXiv",
    "archive_location": "2510.02250",
    "author": [
      {
        "literal": "Gonzalo Gonzalez-Pumariega"
      },
      {
        "literal": "Vincent Tu"
      },
      {
        "literal": "Chih-Lun Lee"
      },
      {
        "literal": "Jiachen Yang"
      },
      {
        "literal": "Ang Li"
      },
      {
        "literal": "Xin Eric Wang"
      }
    ],
    "citation-key": "arxiv_2510_02250",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "29c00ba4713da26f912fec8046d498b4fd10cf71a3109f66e92fa23f7cebcf44",
        "submitted_at": "2025-10-02T17:37:08Z",
        "updated_at": "2026-02-03T23:48:45Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2510.02250v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2510.02250",
      "catalog_id": "arxiv:2510.02250",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-10-02",
      "identifiers": {
        "arxiv": "2510.02250"
      },
      "record_updated_at": "2026-02-03"
    },
    "genre": "preprint",
    "id": "arxiv:2510.02250",
    "issued": {
      "date-parts": [
        [
          2025,
          10,
          2
        ]
      ]
    },
    "note": "First published: 2025-10-02; Recorded arXiv version: v2; Recorded version updated: 2026-02-03T23:48:45Z.",
    "title": "Scaling Agents for Computer Use",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2510.06042v3",
    "archive": "arXiv",
    "archive_location": "2510.06042",
    "author": [
      {
        "literal": "Shang Ma"
      },
      {
        "literal": "Xusheng Xiao"
      },
      {
        "literal": "Yanfang Ye"
      }
    ],
    "citation-key": "arxiv_2510_06042",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "4bf0a561460c080b14da6fd13f6d92781e01e52b08dc691fe019e70b88e44c86",
        "submitted_at": "2025-10-07T15:36:04Z",
        "updated_at": "2026-09-27T17:25:57Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2510.06042v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2510.06042",
      "catalog_id": "arxiv:2510.06042",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-10-07",
      "identifiers": {
        "arxiv": "2510.06042"
      },
      "record_updated_at": "2026-09-27"
    },
    "genre": "preprint",
    "id": "arxiv:2510.06042",
    "issued": {
      "date-parts": [
        [
          2025,
          10,
          7
        ]
      ]
    },
    "note": "First published: 2025-10-07; Recorded arXiv version: v3; Recorded version updated: 2026-09-27T17:25:57Z.",
    "title": "Agent+P: Guiding UI Agents via Symbolic Planning",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2510.14621v1",
    "archive": "arXiv",
    "archive_location": "2510.14621",
    "author": [
      {
        "literal": "Yuanyi Song"
      },
      {
        "literal": "Heyuan Huang"
      },
      {
        "literal": "Qiqiang Lin"
      },
      {
        "literal": "Yin Zhao"
      },
      {
        "literal": "Xiangmou Qu"
      },
      {
        "literal": "Jun Wang"
      },
      {
        "literal": "Xingyu Lou"
      },
      {
        "literal": "Weiwen Liu"
      },
      {
        "literal": "Zhuosheng Zhang"
      },
      {
        "literal": "Jun Wang"
      },
      {
        "literal": "Yong Yu"
      },
      {
        "literal": "Weinan Zhang"
      },
      {
        "literal": "Zhaoxiang Wang"
      }
    ],
    "citation-key": "arxiv_2510_14621",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "fc45dc62068c971cd831fc3db64bd3d8995d4e5fd60e9c83953476d4fb24f7f3",
        "submitted_at": "2025-10-16T12:30:05Z",
        "updated_at": "2025-10-16T12:30:05Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2510.14621v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2510.14621",
      "catalog_id": "arxiv:2510.14621",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-10-16",
      "identifiers": {
        "arxiv": "2510.14621"
      },
      "record_updated_at": "2025-10-16"
    },
    "genre": "preprint",
    "id": "arxiv:2510.14621",
    "issued": {
      "date-parts": [
        [
          2025,
          10,
          16
        ]
      ]
    },
    "note": "First published: 2025-10-16; Recorded arXiv version: v1; Recorded version updated: 2025-10-16T12:30:05Z.",
    "title": "ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Tasks",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2510.19949v2",
    "archive": "arXiv",
    "archive_location": "2510.19949",
    "author": [
      {
        "literal": "Mathieu Andreux"
      },
      {
        "literal": "Märt Bakler"
      },
      {
        "literal": "Yanael Barbier"
      },
      {
        "literal": "Hamza Benchekroun"
      },
      {
        "literal": "Emilien Biré"
      },
      {
        "literal": "Antoine Bonnet"
      },
      {
        "literal": "Riaz Bordie"
      },
      {
        "literal": "Nathan Bout"
      },
      {
        "literal": "Matthias Brunel"
      },
      {
        "literal": "Aleix Cambray"
      },
      {
        "literal": "Pierre-Louis Cedoz"
      },
      {
        "literal": "Antoine Chassang"
      },
      {
        "literal": "Gautier Cloix"
      },
      {
        "literal": "Ethan Connelly"
      },
      {
        "literal": "Alexandra Constantinou"
      },
      {
        "literal": "Ramzi De Coster"
      },
      {
        "literal": "Hubert de la Jonquiere"
      },
      {
        "literal": "Aurélien Delfosse"
      },
      {
        "literal": "Maxime Delpit"
      },
      {
        "literal": "Alexis Deprez"
      },
      {
        "literal": "Augustin Derupti"
      },
      {
        "literal": "Mathieu Diaz"
      },
      {
        "literal": "Shannon D'Souza"
      },
      {
        "literal": "Julie Dujardin"
      },
      {
        "literal": "Abai Edmund"
      },
      {
        "literal": "Michael Eickenberg"
      },
      {
        "literal": "Armand Fatalot"
      },
      {
        "literal": "Wissem Felissi"
      },
      {
        "literal": "Isaac Herring"
      },
      {
        "literal": "Xavier Koegler"
      },
      {
        "literal": "Erwan Le Jumeau de Kergaradec"
      },
      {
        "literal": "Aurélien Lac"
      },
      {
        "literal": "Maxime Langevin"
      },
      {
        "literal": "Corentin Lauverjat"
      },
      {
        "literal": "Antonio Loison"
      },
      {
        "literal": "Avshalom Manevich"
      },
      {
        "literal": "Axel Moyal"
      },
      {
        "literal": "Axel Nguyen Kerbel"
      },
      {
        "literal": "Marinela Parovic"
      },
      {
        "literal": "Julien Revelle"
      },
      {
        "literal": "Guillaume Richard"
      },
      {
        "literal": "Mats Richter"
      },
      {
        "literal": "Ronan Riochet"
      },
      {
        "literal": "María Santos"
      },
      {
        "literal": "Romain Savidan"
      },
      {
        "literal": "Laurent Sifre"
      },
      {
        "literal": "Maxime Theillard"
      },
      {
        "literal": "Marc Thibault"
      },
      {
        "literal": "Ivan Valentini"
      },
      {
        "literal": "Tony Wu"
      },
      {
        "literal": "Laura Yie"
      },
      {
        "literal": "Kai Yuan"
      },
      {
        "literal": "Jevgenij Zubovskij"
      }
    ],
    "citation-key": "arxiv_2510_19949",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "de25494af1bc2ceaa760a21da51803aaf89d9d2d1961887cfd0023fb87f28f63",
        "submitted_at": "2025-10-22T18:21:52Z",
        "updated_at": "2025-10-24T11:52:29Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2510.19949v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2510.19949",
      "catalog_id": "arxiv:2510.19949",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-10-22",
      "identifiers": {
        "arxiv": "2510.19949"
      },
      "record_updated_at": "2025-10-24"
    },
    "genre": "preprint",
    "id": "arxiv:2510.19949",
    "issued": {
      "date-parts": [
        [
          2025,
          10,
          22
        ]
      ]
    },
    "note": "First published: 2025-10-22; Recorded arXiv version: v2; Recorded version updated: 2025-10-24T11:52:29Z.",
    "title": "Surfer 2: The Next Generation of Cross-Platform Computer Use Agents",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2510.24168v3",
    "archive": "arXiv",
    "archive_location": "2510.24168",
    "author": [
      {
        "literal": "Weihua Cheng"
      },
      {
        "literal": "Junming Liu"
      },
      {
        "literal": "Yifei Sun"
      },
      {
        "literal": "Botian Shi"
      },
      {
        "literal": "Yirong Chen"
      },
      {
        "literal": "Ding Wang"
      }
    ],
    "citation-key": "arxiv_2510_24168",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "d80312fbd8f57cdc53cc10e03f2c68e2152d06945e5089967dceda50c02b9d4b",
        "submitted_at": "2025-10-28T08:19:58Z",
        "updated_at": "2026-04-14T04:34:20Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2510.24168v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2510.24168",
      "catalog_id": "arxiv:2510.24168",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-10-28",
      "identifiers": {
        "arxiv": "2510.24168"
      },
      "record_updated_at": "2026-04-14"
    },
    "genre": "preprint",
    "id": "arxiv:2510.24168",
    "issued": {
      "date-parts": [
        [
          2025,
          10,
          28
        ]
      ]
    },
    "note": "First published: 2025-10-28; Recorded arXiv version: v3; Recorded version updated: 2026-04-14T04:34:20Z.",
    "title": "MGA: Memory-Driven GUI Agent for Observation-Centric Interaction",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2511.12254v3",
    "archive": "arXiv",
    "archive_location": "2511.12254",
    "author": [
      {
        "literal": "Yuxiang Zhou"
      },
      {
        "literal": "Jichang Li"
      },
      {
        "literal": "Yanhao Zhang"
      },
      {
        "literal": "Haonan Lu"
      },
      {
        "literal": "Guanbin Li"
      }
    ],
    "citation-key": "arxiv_2511_12254",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "ede08df1c10d8eeede43af75d26608b4917dd83becde23f28cd3adf335f79736",
        "submitted_at": "2025-11-15T15:22:42Z",
        "updated_at": "2026-03-12T08:45:07Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2511.12254v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2511.12254",
      "catalog_id": "arxiv:2511.12254",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-11-15",
      "identifiers": {
        "arxiv": "2511.12254"
      },
      "record_updated_at": "2026-03-12"
    },
    "genre": "preprint",
    "id": "arxiv:2511.12254",
    "issued": {
      "date-parts": [
        [
          2025,
          11,
          15
        ]
      ]
    },
    "note": "First published: 2025-11-15; Recorded arXiv version: v3; Recorded version updated: 2026-03-12T08:45:07Z.",
    "title": "Mobile-Agent-RAG: Driving Smart Multi-Agent Coordination with Contextual Knowledge Empowerment for Long-Horizon Mobile Automation",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2511.22235v2",
    "archive": "arXiv",
    "archive_location": "2511.22235",
    "author": [
      {
        "literal": "Zehao Deng"
      },
      {
        "literal": "Tianjie Ju"
      },
      {
        "literal": "Zheng Wu"
      },
      {
        "literal": "Zhuosheng Zhang"
      },
      {
        "literal": "Gongshen Liu"
      }
    ],
    "citation-key": "arxiv_2511_22235",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "9acb395dfaad18b84ea4b52d97be194a42eb42d6ac922c55f2179e38cc258a31",
        "submitted_at": "2025-11-27T09:01:38Z",
        "updated_at": "2026-03-04T12:15:06Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2511.22235v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2511.22235",
      "catalog_id": "arxiv:2511.22235",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-11-27",
      "identifiers": {
        "arxiv": "2511.22235"
      },
      "record_updated_at": "2026-03-04"
    },
    "genre": "preprint",
    "id": "arxiv:2511.22235",
    "issued": {
      "date-parts": [
        [
          2025,
          11,
          27
        ]
      ]
    },
    "note": "First published: 2025-11-27; Recorded arXiv version: v2; Recorded version updated: 2026-03-04T12:15:06Z.",
    "title": "Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI Automation",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2512.10371v2",
    "archive": "arXiv",
    "archive_location": "2512.10371",
    "author": [
      {
        "literal": "Shizuo Tian"
      },
      {
        "literal": "Hao Wen"
      },
      {
        "literal": "Yuxuan Chen"
      },
      {
        "literal": "Jiacheng Liu"
      },
      {
        "literal": "Shanhui Zhao"
      },
      {
        "literal": "Guohong Liu"
      },
      {
        "literal": "Ju Ren"
      },
      {
        "literal": "Yunxin Liu"
      },
      {
        "literal": "Yuanchun Li"
      }
    ],
    "citation-key": "arxiv_2512_10371",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "72b2db237a52ae31eaba58183a2777e79379aa8e849d18de5d8633daf27ccbf9",
        "submitted_at": "2025-12-11T07:37:38Z",
        "updated_at": "2026-05-08T09:40:02Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2512.10371v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2512.10371",
      "catalog_id": "arxiv:2512.10371",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-12-11",
      "identifiers": {
        "arxiv": "2512.10371"
      },
      "record_updated_at": "2026-05-08"
    },
    "genre": "preprint",
    "id": "arxiv:2512.10371",
    "issued": {
      "date-parts": [
        [
          2025,
          12,
          11
        ]
      ]
    },
    "note": "First published: 2025-12-11; Recorded arXiv version: v2; Recorded version updated: 2026-05-08T09:40:02Z.",
    "title": "AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2512.19432v3",
    "archive": "arXiv",
    "archive_location": "2512.19432",
    "author": [
      {
        "literal": "Quyu Kong"
      },
      {
        "literal": "Xu Zhang"
      },
      {
        "literal": "Zhenyu Yang"
      },
      {
        "literal": "Nolan Gao"
      },
      {
        "literal": "Chen Liu"
      },
      {
        "literal": "Panrong Tong"
      },
      {
        "literal": "Chenglin Cai"
      },
      {
        "literal": "Hanzhang Zhou"
      },
      {
        "literal": "Jianan Zhang"
      },
      {
        "literal": "Liangyu Chen"
      },
      {
        "literal": "Zhidan Liu"
      },
      {
        "literal": "Steven Hoi"
      },
      {
        "literal": "Yue Wang"
      }
    ],
    "citation-key": "arxiv_2512_19432",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "cf3258fd2286b0ee6babb69b9bfc459ecf40536eec498a3af3403d2971791f3d",
        "submitted_at": "2025-12-22T14:31:28Z",
        "updated_at": "2025-12-30T07:15:15Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2512.19432v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2512.19432",
      "catalog_id": "arxiv:2512.19432",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-12-22",
      "identifiers": {
        "arxiv": "2512.19432"
      },
      "record_updated_at": "2025-12-30"
    },
    "genre": "preprint",
    "id": "arxiv:2512.19432",
    "issued": {
      "date-parts": [
        [
          2025,
          12,
          22
        ]
      ]
    },
    "note": "First published: 2025-12-22; Recorded arXiv version: v3; Recorded version updated: 2025-12-30T07:15:15Z.",
    "title": "MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2512.21302v1",
    "archive": "arXiv",
    "archive_location": "2512.21302",
    "author": [
      {
        "literal": "Yue Cao"
      },
      {
        "literal": "Yingyao Wang"
      },
      {
        "literal": "Pi Bu"
      },
      {
        "literal": "Jingxuan Xing"
      },
      {
        "literal": "Wei Jiang"
      },
      {
        "literal": "Zekun Zhu"
      },
      {
        "literal": "Junpeng Ma"
      },
      {
        "literal": "Sashuai Zhou"
      },
      {
        "literal": "Tong Lu"
      },
      {
        "literal": "Jun Song"
      },
      {
        "literal": "Yu Cheng"
      },
      {
        "literal": "Yuning Jiang"
      },
      {
        "literal": "Bo Zheng"
      }
    ],
    "citation-key": "arxiv_2512_21302",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "597935923ce9e59720771f3d92e921f2842f908ad81b3ab31a87ed9d9f5c5774",
        "submitted_at": "2025-12-24T17:40:42Z",
        "updated_at": "2025-12-24T17:40:42Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2512.21302v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2512.21302",
      "catalog_id": "arxiv:2512.21302",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2025-12-24",
      "identifiers": {
        "arxiv": "2512.21302"
      },
      "record_updated_at": "2025-12-24"
    },
    "genre": "preprint",
    "id": "arxiv:2512.21302",
    "issued": {
      "date-parts": [
        [
          2025,
          12,
          24
        ]
      ]
    },
    "note": "First published: 2025-12-24; Recorded arXiv version: v1; Recorded version updated: 2025-12-24T17:40:42Z.",
    "title": "AndroidLens: Long-latency Evaluation with Nested Sub-targets for Android GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2601.07262v3",
    "archive": "arXiv",
    "archive_location": "2601.07262",
    "author": [
      {
        "literal": "Jihong Wang"
      },
      {
        "literal": "Jiamu Zhou"
      },
      {
        "literal": "Weiming Zhang"
      },
      {
        "literal": "Teng Wang"
      },
      {
        "literal": "Weiwen Liu"
      },
      {
        "literal": "Zhuosheng Zhang"
      },
      {
        "literal": "Xingyu Lou"
      },
      {
        "literal": "Weinan Zhang"
      },
      {
        "literal": "Huarong Deng"
      },
      {
        "literal": "Jun Wang"
      }
    ],
    "citation-key": "arxiv_2601_07262",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "a2afe8d0d8d83f91003b7885635e098e19f69024306c43c3edb23c110e553f63",
        "submitted_at": "2026-01-12T07:08:42Z",
        "updated_at": "2026-04-23T09:34:51Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2601.07262v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2601.07262",
      "catalog_id": "arxiv:2601.07262",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-01-12",
      "identifiers": {
        "arxiv": "2601.07262"
      },
      "record_updated_at": "2026-04-23"
    },
    "genre": "preprint",
    "id": "arxiv:2601.07262",
    "issued": {
      "date-parts": [
        [
          2026,
          1,
          12
        ]
      ]
    },
    "note": "First published: 2026-01-12; Recorded arXiv version: v3; Recorded version updated: 2026-04-23T09:34:51Z.",
    "title": "ColorBrowserAgent: Complex Long-Horizon Browser Agent with Adaptive Knowledge Evolution",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2601.15876v2",
    "archive": "arXiv",
    "archive_location": "2601.15876",
    "author": [
      {
        "literal": "Taofeng Xue"
      },
      {
        "literal": "Chong Peng"
      },
      {
        "literal": "Mianqiu Huang"
      },
      {
        "literal": "Linsen Guo"
      },
      {
        "literal": "Tiancheng Han"
      },
      {
        "literal": "Haozhe Wang"
      },
      {
        "literal": "Jianing Wang"
      },
      {
        "literal": "Xiaocheng Zhang"
      },
      {
        "literal": "Xin Yang"
      },
      {
        "literal": "Dengchang Zhao"
      },
      {
        "literal": "Jinrui Ding"
      },
      {
        "literal": "Xiandi Ma"
      },
      {
        "literal": "Yuchen Xie"
      },
      {
        "literal": "Peng Pei"
      },
      {
        "literal": "Xunliang Cai"
      },
      {
        "literal": "Xipeng Qiu"
      }
    ],
    "citation-key": "arxiv_2601_15876",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "38b2798ce9ebd69a46202f0fa8ceca859394acda4f5173b5e30248914c8c35ac",
        "submitted_at": "2026-01-22T11:36:43Z",
        "updated_at": "2026-01-23T08:52:00Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2601.15876v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2601.15876",
      "catalog_id": "arxiv:2601.15876",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-01-22",
      "identifiers": {
        "arxiv": "2601.15876"
      },
      "record_updated_at": "2026-01-23"
    },
    "genre": "preprint",
    "id": "arxiv:2601.15876",
    "issued": {
      "date-parts": [
        [
          2026,
          1,
          22
        ]
      ]
    },
    "note": "First published: 2026-01-22; Recorded arXiv version: v2; Recorded version updated: 2026-01-23T08:52:00Z.",
    "title": "EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2601.20650v3",
    "archive": "arXiv",
    "archive_location": "2601.20650",
    "author": [
      {
        "literal": "Jing Wu"
      },
      {
        "literal": "Wenjie Ai"
      },
      {
        "literal": "Daphne Barretto"
      },
      {
        "literal": "Yiye Chen"
      },
      {
        "literal": "Qingyu Chen"
      },
      {
        "literal": "Yuhang He"
      },
      {
        "literal": "Pranit Chawla"
      },
      {
        "literal": "Nicholas Gydé"
      },
      {
        "literal": "Yanan Jian"
      },
      {
        "literal": "Vibhav Vineet"
      }
    ],
    "citation-key": "arxiv_2601_20650",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "0139f7a1402d8dbfdecf65cc53c032495b2084f24cc38ff43841642c9102f29c",
        "submitted_at": "2026-01-28T14:35:23Z",
        "updated_at": "2026-08-26T22:31:44Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2601.20650v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2601.20650",
      "catalog_id": "arxiv:2601.20650",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-01-28",
      "identifiers": {
        "arxiv": "2601.20650"
      },
      "record_updated_at": "2026-08-26"
    },
    "genre": "preprint",
    "id": "arxiv:2601.20650",
    "issued": {
      "date-parts": [
        [
          2026,
          1,
          28
        ]
      ]
    },
    "note": "First published: 2026-01-28; Recorded arXiv version: v3; Recorded version updated: 2026-08-26T22:31:44Z.",
    "title": "OS-Marathon: Benchmarking Computer-Use Agents on Vast-Horizon, Repetitive Tasks",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2601.21352v1",
    "archive": "arXiv",
    "archive_location": "2601.21352",
    "author": [
      {
        "literal": "Ziyu Lu"
      },
      {
        "literal": "Tengjin Weng"
      },
      {
        "literal": "Yiying Yang"
      },
      {
        "literal": "Yuhang Zhao"
      },
      {
        "literal": "Xinxin Huang"
      },
      {
        "literal": "Wenhao Jiang"
      }
    ],
    "citation-key": "arxiv_2601_21352",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "fa36a9fbd0b189717b2a5311f06b6127d54f2eca09961cedd2a0b9d2a78b1b8b",
        "submitted_at": "2026-01-29T07:22:50Z",
        "updated_at": "2026-01-29T07:22:50Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2601.21352v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2601.21352",
      "catalog_id": "arxiv:2601.21352",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-01-29",
      "identifiers": {
        "arxiv": "2601.21352"
      },
      "record_updated_at": "2026-01-29"
    },
    "genre": "preprint",
    "id": "arxiv:2601.21352",
    "issued": {
      "date-parts": [
        [
          2026,
          1,
          29
        ]
      ]
    },
    "note": "First published: 2026-01-29; Recorded arXiv version: v1; Recorded version updated: 2026-01-29T07:22:50Z.",
    "title": "BEAP-Agent: Backtrackable Execution and Adaptive Planning for GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2601.22528v1",
    "archive": "arXiv",
    "archive_location": "2601.22528",
    "author": [
      {
        "literal": "Hongze Mi"
      },
      {
        "literal": "Yibo Feng"
      },
      {
        "literal": "WenJie Lu"
      },
      {
        "literal": "Song Cao"
      },
      {
        "literal": "Jinyuan Li"
      },
      {
        "literal": "Yanming Li"
      },
      {
        "literal": "Xuelin Zhang"
      },
      {
        "literal": "Haotian Luo"
      },
      {
        "literal": "Songyang Peng"
      },
      {
        "literal": "He Cui"
      },
      {
        "literal": "Tengfei Tian"
      },
      {
        "literal": "Jun Fang"
      },
      {
        "literal": "Hua Chai"
      },
      {
        "literal": "Naiqiang Tan"
      }
    ],
    "citation-key": "arxiv_2601_22528",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "c0b3dbaacdf640a1314a40688133f7386c0eb8b901c43393ad21ec887814a606",
        "submitted_at": "2026-01-30T04:01:21Z",
        "updated_at": "2026-01-30T04:01:21Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2601.22528v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2601.22528",
      "catalog_id": "arxiv:2601.22528",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-01-30",
      "identifiers": {
        "arxiv": "2601.22528"
      },
      "record_updated_at": "2026-01-30"
    },
    "genre": "preprint",
    "id": "arxiv:2601.22528",
    "issued": {
      "date-parts": [
        [
          2026,
          1,
          30
        ]
      ]
    },
    "note": "First published: 2026-01-30; Recorded arXiv version: v1; Recorded version updated: 2026-01-30T04:01:21Z.",
    "title": "Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolution",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2602.16313v2",
    "archive": "arXiv",
    "archive_location": "2602.16313",
    "author": [
      {
        "literal": "Zexue He"
      },
      {
        "literal": "Yu Wang"
      },
      {
        "literal": "Churan Zhi"
      },
      {
        "literal": "Yuanzhe Hu"
      },
      {
        "literal": "Tzu-Ping Chen"
      },
      {
        "literal": "Lang Yin"
      },
      {
        "literal": "Ze Chen"
      },
      {
        "literal": "Tong Arthur Wu"
      },
      {
        "literal": "Siru Ouyang"
      },
      {
        "literal": "Zihan Wang"
      },
      {
        "literal": "Jiaxin Pei"
      },
      {
        "literal": "Julian McAuley"
      },
      {
        "literal": "Yejin Choi"
      },
      {
        "literal": "Alex Pentland"
      }
    ],
    "citation-key": "arxiv_2602_16313",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "2317a94d54b4458a1b7c5e92754aeaefcbf270aabfa0bd8ea333c673cd4596b3",
        "submitted_at": "2026-02-18T09:49:14Z",
        "updated_at": "2026-09-17T22:55:03Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2602.16313v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2602.16313",
      "catalog_id": "arxiv:2602.16313",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-02-18",
      "identifiers": {
        "arxiv": "2602.16313"
      },
      "record_updated_at": "2026-09-17"
    },
    "genre": "preprint",
    "id": "arxiv:2602.16313",
    "issued": {
      "date-parts": [
        [
          2026,
          2,
          18
        ]
      ]
    },
    "note": "First published: 2026-02-18; Recorded arXiv version: v2; Recorded version updated: 2026-09-17T22:55:03Z.",
    "title": "MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2603.18429v1",
    "archive": "arXiv",
    "archive_location": "2603.18429",
    "author": [
      {
        "literal": "Yibo Shi"
      },
      {
        "literal": "Jungang Li"
      },
      {
        "literal": "Linghao Zhang"
      },
      {
        "literal": "Zihao Dongfang"
      },
      {
        "literal": "Biao Wu"
      },
      {
        "literal": "Sicheng Tao"
      },
      {
        "literal": "Yibo Yan"
      },
      {
        "literal": "Chenxi Qin"
      },
      {
        "literal": "Weiting Liu"
      },
      {
        "literal": "Zhixin Lin"
      },
      {
        "literal": "Hanqian Li"
      },
      {
        "literal": "Yu Huang"
      },
      {
        "literal": "Song Dai"
      },
      {
        "literal": "Yonghua Hei"
      },
      {
        "literal": "Yue Ding"
      },
      {
        "literal": "Xiang Li"
      },
      {
        "literal": "Shikang Wang"
      },
      {
        "literal": "Chengdong Xu"
      },
      {
        "literal": "Jingqi Liu"
      },
      {
        "literal": "Xueying Ma"
      },
      {
        "literal": "Zhiwen Zheng"
      },
      {
        "literal": "Xiaofei Zhang"
      },
      {
        "literal": "Bincheng Wang"
      },
      {
        "literal": "Nichen Yang"
      },
      {
        "literal": "Jie Wu"
      },
      {
        "literal": "Lihua Tian"
      },
      {
        "literal": "Chen Li"
      },
      {
        "literal": "Xuming Hu"
      }
    ],
    "citation-key": "arxiv_2603_18429",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "0ce6da91e59ac57fa24ff991ca023b84448c54d477cacb2d6fded9bf527dd29d",
        "submitted_at": "2026-03-19T02:45:21Z",
        "updated_at": "2026-03-19T02:45:21Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2603.18429v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2603.18429",
      "catalog_id": "arxiv:2603.18429",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-03-19",
      "identifiers": {
        "arxiv": "2603.18429"
      },
      "record_updated_at": "2026-03-19"
    },
    "genre": "preprint",
    "id": "arxiv:2603.18429",
    "issued": {
      "date-parts": [
        [
          2026,
          3,
          19
        ]
      ]
    },
    "note": "First published: 2026-03-19; Recorded arXiv version: v1; Recorded version updated: 2026-03-19T02:45:21Z.",
    "title": "AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2603.19685v1",
    "archive": "arXiv",
    "archive_location": "2603.19685",
    "author": [
      {
        "literal": "Taiyi Wang"
      },
      {
        "literal": "Sian Gooding"
      },
      {
        "literal": "Florian Hartmann"
      },
      {
        "literal": "Oriana Riva"
      },
      {
        "literal": "Edward Grefenstette"
      }
    ],
    "citation-key": "arxiv_2603_19685",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "5538933a0e3d11df6ff4d767849979703d83412599fbbb0f8b432c4d9850633b",
        "submitted_at": "2026-03-20T06:32:16Z",
        "updated_at": "2026-03-20T06:32:16Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2603.19685v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2603.19685",
      "catalog_id": "arxiv:2603.19685",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-03-20",
      "identifiers": {
        "arxiv": "2603.19685"
      },
      "record_updated_at": "2026-03-20"
    },
    "genre": "preprint",
    "id": "arxiv:2603.19685",
    "issued": {
      "date-parts": [
        [
          2026,
          3,
          20
        ]
      ]
    },
    "note": "First published: 2026-03-20; Recorded arXiv version: v1; Recorded version updated: 2026-03-20T06:32:16Z.",
    "title": "A Subgoal-driven Framework for Improving Long-Horizon LLM Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2603.24157v1",
    "archive": "arXiv",
    "archive_location": "2603.24157",
    "author": [
      {
        "literal": "Akash Ghosh"
      },
      {
        "literal": "Tajamul Ashraf"
      },
      {
        "literal": "Rishu Kumar Singh"
      },
      {
        "literal": "Numan Saeed"
      },
      {
        "literal": "Sriparna Saha"
      },
      {
        "literal": "Xiuying Chen"
      },
      {
        "literal": "Salman Khan"
      }
    ],
    "citation-key": "arxiv_2603_24157",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "8fb6a294616e1be46c5da05f60cda7d43c05d8a1ce71116c5e30cb94507cd56f",
        "submitted_at": "2026-03-25T10:25:48Z",
        "updated_at": "2026-03-25T10:25:48Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2603.24157v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2603.24157",
      "catalog_id": "arxiv:2603.24157",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-03-25",
      "identifiers": {
        "arxiv": "2603.24157"
      },
      "record_updated_at": "2026-03-25"
    },
    "genre": "preprint",
    "id": "arxiv:2603.24157",
    "issued": {
      "date-parts": [
        [
          2026,
          3,
          25
        ]
      ]
    },
    "note": "First published: 2026-03-25; Recorded arXiv version: v1; Recorded version updated: 2026-03-25T10:25:48Z.",
    "title": "CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcare",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2604.04399v1",
    "archive": "arXiv",
    "archive_location": "2604.04399",
    "author": [
      {
        "literal": "Yuwen Zhai"
      },
      {
        "literal": "Runze Li"
      },
      {
        "literal": "Liang Wang"
      },
      {
        "literal": "Nian Shi"
      },
      {
        "literal": "Liwu Xu"
      },
      {
        "literal": "Wei Zhang"
      },
      {
        "literal": "Ran Lin"
      },
      {
        "literal": "Bo Xu"
      },
      {
        "literal": "Benlei Cui"
      }
    ],
    "citation-key": "arxiv_2604_04399",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "856e9920aea7d821061b3258b31aa32fd37b5579d628f5507f45ba83f237b77b",
        "submitted_at": "2026-04-06T03:58:43Z",
        "updated_at": "2026-04-06T03:58:43Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2604.04399v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2604.04399",
      "catalog_id": "arxiv:2604.04399",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-04-06",
      "identifiers": {
        "arxiv": "2604.04399"
      },
      "record_updated_at": "2026-04-06"
    },
    "genre": "preprint",
    "id": "arxiv:2604.04399",
    "issued": {
      "date-parts": [
        [
          2026,
          4,
          6
        ]
      ]
    },
    "note": "First published: 2026-04-06; Recorded arXiv version: v1; Recorded version updated: 2026-04-06T03:58:43Z.",
    "title": "GUIDE: Interpretable GUI Agent Evaluation via Hierarchical Diagnosis",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2604.06126v1",
    "archive": "arXiv",
    "archive_location": "2604.06126",
    "author": [
      {
        "literal": "Pranjal Aggarwal"
      },
      {
        "literal": "Graham Neubig"
      },
      {
        "literal": "Sean Welleck"
      }
    ],
    "citation-key": "arxiv_2604_06126",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "fdd9cb6daad8832261ebe861fc1cb74429b819305e14ecfeb9698616013e6ac8",
        "submitted_at": "2026-04-07T17:38:15Z",
        "updated_at": "2026-04-07T17:38:15Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2604.06126v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2604.06126",
      "catalog_id": "arxiv:2604.06126",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-04-07",
      "identifiers": {
        "arxiv": "2604.06126"
      },
      "record_updated_at": "2026-04-07"
    },
    "genre": "preprint",
    "id": "arxiv:2604.06126",
    "issued": {
      "date-parts": [
        [
          2026,
          4,
          7
        ]
      ]
    },
    "note": "First published: 2026-04-07; Recorded arXiv version: v1; Recorded version updated: 2026-04-07T17:38:15Z.",
    "title": "Gym-Anything: Turn any Software into an Agent Environment",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2604.06240v1",
    "archive": "arXiv",
    "archive_location": "2604.06240",
    "author": [
      {
        "literal": "Corby Rosset"
      },
      {
        "literal": "Pratyusha Sharma"
      },
      {
        "literal": "Andrew Zhao"
      },
      {
        "literal": "Miguel Gonzalez-Fernandez"
      },
      {
        "literal": "Ahmed Awadallah"
      }
    ],
    "citation-key": "arxiv_2604_06240",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "b452684b305c4f20ded686289b448fbe4f08bb3b34f515a43e2ce5d6dc4ef506",
        "submitted_at": "2026-04-05T06:26:05Z",
        "updated_at": "2026-04-05T06:26:05Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2604.06240v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2604.06240",
      "catalog_id": "arxiv:2604.06240",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-04-05",
      "identifiers": {
        "arxiv": "2604.06240"
      },
      "record_updated_at": "2026-04-05"
    },
    "genre": "preprint",
    "id": "arxiv:2604.06240",
    "issued": {
      "date-parts": [
        [
          2026,
          4,
          5
        ]
      ]
    },
    "note": "First published: 2026-04-05; Recorded arXiv version: v1; Recorded version updated: 2026-04-05T06:26:05Z.",
    "title": "The Art of Building Verifiers for Computer Use Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2604.13822v1",
    "archive": "arXiv",
    "archive_location": "2604.13822",
    "author": [
      {
        "literal": "Zhengxi Lu"
      },
      {
        "literal": "Fei Tang"
      },
      {
        "literal": "Guangyi Liu"
      },
      {
        "literal": "Kaitao Song"
      },
      {
        "literal": "Xu Tan"
      },
      {
        "literal": "Jin Ma"
      },
      {
        "literal": "Wenqi Zhang"
      },
      {
        "literal": "Weiming Lu"
      },
      {
        "literal": "Jun Xiao"
      },
      {
        "literal": "Yueting Zhuang"
      },
      {
        "literal": "Yongliang Shen"
      }
    ],
    "citation-key": "arxiv_2604_13822",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "d6e81b448c9c22e2fd25dce519db3fdc0585b0265b94d448751d7a37ed910dfa",
        "submitted_at": "2026-04-15T12:55:46Z",
        "updated_at": "2026-04-15T12:55:46Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2604.13822v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2604.13822",
      "catalog_id": "arxiv:2604.13822",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-04-15",
      "identifiers": {
        "arxiv": "2604.13822"
      },
      "record_updated_at": "2026-04-15"
    },
    "genre": "preprint",
    "id": "arxiv:2604.13822",
    "issued": {
      "date-parts": [
        [
          2026,
          4,
          15
        ]
      ]
    },
    "note": "First published: 2026-04-15; Recorded arXiv version: v1; Recorded version updated: 2026-04-15T12:55:46Z.",
    "title": "UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2604.17821v2",
    "archive": "arXiv",
    "archive_location": "2604.17821",
    "author": [
      {
        "literal": "Lingfeng Zhang"
      },
      {
        "literal": "Yongan Sun"
      },
      {
        "literal": "Jinpeng Hu"
      },
      {
        "literal": "Hui Ma"
      },
      {
        "literal": "Yang Ying"
      },
      {
        "literal": "Kuien Liu"
      },
      {
        "literal": "Zenglin Shi"
      },
      {
        "literal": "Meng Wang"
      }
    ],
    "citation-key": "arxiv_2604_17821",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "123577fbb4431f22bc18d2d32187744268f9d63b3149e9e1775fb44673771feb",
        "submitted_at": "2026-04-20T05:19:49Z",
        "updated_at": "2026-04-21T03:15:01Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2604.17821v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2604.17821",
      "catalog_id": "arxiv:2604.17821",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-04-20",
      "identifiers": {
        "arxiv": "2604.17821"
      },
      "record_updated_at": "2026-04-21"
    },
    "genre": "preprint",
    "id": "arxiv:2604.17821",
    "issued": {
      "date-parts": [
        [
          2026,
          4,
          20
        ]
      ]
    },
    "note": "First published: 2026-04-20; Recorded arXiv version: v2; Recorded version updated: 2026-04-21T03:15:01Z.",
    "title": "WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2604.24964v1",
    "archive": "arXiv",
    "archive_location": "2604.24964",
    "author": [
      {
        "literal": "Lawrence Keunho Jang"
      },
      {
        "literal": "Jing Yu Koh"
      },
      {
        "literal": "Daniel Fried"
      },
      {
        "literal": "Ruslan Salakhutdinov"
      }
    ],
    "citation-key": "arxiv_2604_24964",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "db70a5736d04d26f10afe3d9a0cfb08955f65f69480a0345ff13b30b2e83df23",
        "submitted_at": "2026-04-27T20:05:41Z",
        "updated_at": "2026-04-27T20:05:41Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2604.24964v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2604.24964",
      "catalog_id": "arxiv:2604.24964",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-04-27",
      "identifiers": {
        "arxiv": "2604.24964"
      },
      "record_updated_at": "2026-04-27"
    },
    "genre": "preprint",
    "id": "arxiv:2604.24964",
    "issued": {
      "date-parts": [
        [
          2026,
          4,
          27
        ]
      ]
    },
    "note": "First published: 2026-04-27; Recorded arXiv version: v1; Recorded version updated: 2026-04-27T20:05:41Z.",
    "title": "Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2604.27151v1",
    "archive": "arXiv",
    "archive_location": "2604.27151",
    "author": [
      {
        "literal": "Jinbiao Wei"
      },
      {
        "literal": "Kangqi Ni"
      },
      {
        "literal": "Yilun Zhao"
      },
      {
        "literal": "Guo Gan"
      },
      {
        "literal": "Arman Cohan"
      }
    ],
    "citation-key": "arxiv_2604_27151",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "68183be37dbd78314aca35f7f1420e5f2f8da8d8c0042a258b45ae03c90606cf",
        "submitted_at": "2026-04-29T19:59:36Z",
        "updated_at": "2026-04-29T19:59:36Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2604.27151v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2604.27151",
      "catalog_id": "arxiv:2604.27151",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-04-29",
      "identifiers": {
        "arxiv": "2604.27151"
      },
      "record_updated_at": "2026-04-29"
    },
    "genre": "preprint",
    "id": "arxiv:2604.27151",
    "issued": {
      "date-parts": [
        [
          2026,
          4,
          29
        ]
      ]
    },
    "note": "First published: 2026-04-29; Recorded arXiv version: v1; Recorded version updated: 2026-04-29T19:59:36Z.",
    "title": "Step-level Optimization for Efficient Computer-use Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2605.09317v1",
    "archive": "arXiv",
    "archive_location": "2605.09317",
    "author": [
      {
        "literal": "Guibin Zhang"
      },
      {
        "literal": "Yaohui Ling"
      },
      {
        "literal": "Fanci Meng"
      },
      {
        "literal": "Kun Wang"
      },
      {
        "literal": "Shuicheng Yan"
      }
    ],
    "citation-key": "arxiv_2605_09317",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "729ff6b37da62bb8a9a911865554520e3b29219d9735e087c3186705428d7b05",
        "submitted_at": "2026-05-10T04:31:23Z",
        "updated_at": "2026-05-10T04:31:23Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2605.09317v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2605.09317",
      "catalog_id": "arxiv:2605.09317",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-05-10",
      "identifiers": {
        "arxiv": "2605.09317"
      },
      "record_updated_at": "2026-05-10"
    },
    "genre": "preprint",
    "id": "arxiv:2605.09317",
    "issued": {
      "date-parts": [
        [
          2026,
          5,
          10
        ]
      ]
    },
    "note": "First published: 2026-05-10; Recorded arXiv version: v1; Recorded version updated: 2026-05-10T04:31:23Z.",
    "title": "Mem-W: Latent Memory-Native GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2605.12294v1",
    "archive": "arXiv",
    "archive_location": "2605.12294",
    "author": [
      {
        "literal": "Zerui Qin"
      },
      {
        "literal": "Sheng Yue"
      },
      {
        "literal": "Xingyuan Hua"
      },
      {
        "literal": "Yongjian Fu"
      },
      {
        "literal": "Ju Ren"
      }
    ],
    "citation-key": "arxiv_2605_12294",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "388eac2721929fc8211f40cc4edde61be0b6e6145fa60fbaa444ec80822fcc36",
        "submitted_at": "2026-05-12T15:48:44Z",
        "updated_at": "2026-05-12T15:48:44Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2605.12294v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2605.12294",
      "catalog_id": "arxiv:2605.12294",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-05-12",
      "identifiers": {
        "arxiv": "2605.12294"
      },
      "record_updated_at": "2026-05-12"
    },
    "genre": "preprint",
    "id": "arxiv:2605.12294",
    "issued": {
      "date-parts": [
        [
          2026,
          5,
          12
        ]
      ]
    },
    "note": "First published: 2026-05-12; Recorded arXiv version: v1; Recorded version updated: 2026-05-12T15:48:44Z.",
    "title": "Executable Agentic Memory for GUI Agent",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2605.15777v2",
    "archive": "arXiv",
    "archive_location": "2605.15777",
    "author": [
      {
        "literal": "Kean Shi"
      },
      {
        "literal": "Zihang Li"
      },
      {
        "literal": "Tianyi Ma"
      },
      {
        "literal": "Zengji Tu"
      },
      {
        "literal": "Jialong Wu"
      },
      {
        "literal": "Xinbo Xu"
      },
      {
        "literal": "Qingyao Yang"
      },
      {
        "literal": "Ruoyu Wu"
      },
      {
        "literal": "Weichu Xie"
      },
      {
        "literal": "Ming Wu"
      },
      {
        "literal": "Jason Zeng"
      },
      {
        "literal": "Michael Heinrich"
      },
      {
        "literal": "Elvis Zhang"
      },
      {
        "literal": "Liang Chen"
      },
      {
        "literal": "Kuan Li"
      },
      {
        "literal": "Baobao Chang"
      }
    ],
    "citation-key": "arxiv_2605_15777",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "c4ee2439dd31a375b6f64cbc7f1d0ff75c87e1346b1627a53db145ae42682f8a",
        "submitted_at": "2026-05-15T09:35:15Z",
        "updated_at": "2026-05-24T16:35:56Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2605.15777v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2605.15777",
      "catalog_id": "arxiv:2605.15777",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-05-15",
      "identifiers": {
        "arxiv": "2605.15777"
      },
      "record_updated_at": "2026-05-24"
    },
    "genre": "preprint",
    "id": "arxiv:2605.15777",
    "issued": {
      "date-parts": [
        [
          2026,
          5,
          15
        ]
      ]
    },
    "note": "First published: 2026-05-15; Recorded arXiv version: v2; Recorded version updated: 2026-05-24T16:35:56Z.",
    "title": "SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2605.18652v1",
    "archive": "arXiv",
    "archive_location": "2605.18652",
    "author": [
      {
        "literal": "Ziyun Zeng"
      },
      {
        "literal": "Hang Hua"
      },
      {
        "literal": "Bocheng Zou"
      },
      {
        "literal": "Mu Cai"
      },
      {
        "literal": "Rogerio Feris"
      },
      {
        "literal": "Jiebo Luo"
      }
    ],
    "citation-key": "arxiv_2605_18652",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "d96c8844274f79adea167169a0853e3a7cd82fee4a8a666913f97898a0836e7c",
        "submitted_at": "2026-05-18T16:57:36Z",
        "updated_at": "2026-05-18T16:57:36Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2605.18652v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2605.18652",
      "catalog_id": "arxiv:2605.18652",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-05-18",
      "identifiers": {
        "arxiv": "2605.18652"
      },
      "record_updated_at": "2026-05-18"
    },
    "genre": "preprint",
    "id": "arxiv:2605.18652",
    "issued": {
      "date-parts": [
        [
          2026,
          5,
          18
        ]
      ]
    },
    "note": "First published: 2026-05-18; Recorded arXiv version: v1; Recorded version updated: 2026-05-18T16:57:36Z.",
    "title": "MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2605.26086v1",
    "archive": "arXiv",
    "archive_location": "2605.26086",
    "author": [
      {
        "literal": "Yusong Lin"
      },
      {
        "literal": "Xinyuan Liang"
      },
      {
        "literal": "Haiyang Wang"
      },
      {
        "literal": "Qipeng Gu"
      },
      {
        "literal": "Siqi Cheng"
      },
      {
        "literal": "Jiangui Chen"
      },
      {
        "literal": "Shuzhe Wu"
      },
      {
        "literal": "Feiyang Pan"
      },
      {
        "literal": "Lue Fan"
      },
      {
        "literal": "Sanyuan Zhao"
      },
      {
        "literal": "Dandan Tu"
      }
    ],
    "citation-key": "arxiv_2605_26086",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "27999553928305cfa4223011feb3f9c2decda8a861e5800865537a81c7c08832",
        "submitted_at": "2026-05-25T17:50:04Z",
        "updated_at": "2026-05-25T17:50:04Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2605.26086v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2605.26086",
      "catalog_id": "arxiv:2605.26086",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-05-25",
      "identifiers": {
        "arxiv": "2605.26086"
      },
      "record_updated_at": "2026-05-25"
    },
    "genre": "preprint",
    "id": "arxiv:2605.26086",
    "issued": {
      "date-parts": [
        [
          2026,
          5,
          25
        ]
      ]
    },
    "note": "First published: 2026-05-25; Recorded arXiv version: v1; Recorded version updated: 2026-05-25T17:50:04Z.",
    "title": "Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2605.27761v1",
    "archive": "arXiv",
    "archive_location": "2605.27761",
    "author": [
      {
        "literal": "Yifan Sui"
      },
      {
        "literal": "Xin Huang"
      },
      {
        "literal": "Hongbing Li"
      },
      {
        "literal": "Fang Xu"
      },
      {
        "literal": "Jiahe Lv"
      },
      {
        "literal": "Haolong Yan"
      },
      {
        "literal": "Yeqing Shen"
      },
      {
        "literal": "Litao Liu"
      },
      {
        "literal": "Zhimin Fan"
      },
      {
        "literal": "Ziyang Meng"
      },
      {
        "literal": "Jia Wang"
      },
      {
        "literal": "Junbo Qi"
      },
      {
        "literal": "Kaijun Tan"
      },
      {
        "literal": "Zheng Ge"
      },
      {
        "literal": "Xiangyu Zhang"
      },
      {
        "literal": "Daxin Jiang"
      },
      {
        "literal": "Osamu Yoshie"
      }
    ],
    "citation-key": "arxiv_2605_27761",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "0c89b8b5ef5aa17fe747201285104544648449804cc2229a77577d217763f497",
        "submitted_at": "2026-05-26T23:19:42Z",
        "updated_at": "2026-05-26T23:19:42Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2605.27761v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2605.27761",
      "catalog_id": "arxiv:2605.27761",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-05-26",
      "identifiers": {
        "arxiv": "2605.27761"
      },
      "record_updated_at": "2026-05-26"
    },
    "genre": "preprint",
    "id": "arxiv:2605.27761",
    "issued": {
      "date-parts": [
        [
          2026,
          5,
          26
        ]
      ]
    },
    "note": "First published: 2026-05-26; Recorded arXiv version: v1; Recorded version updated: 2026-05-26T23:19:42Z.",
    "title": "AndroidDaily: A Verifiable Benchmark for Mobile GUI Agents on Real-World Closed-Source Applications",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2606.01533v1",
    "archive": "arXiv",
    "archive_location": "2606.01533",
    "author": [
      {
        "literal": "Jing Yu Koh"
      },
      {
        "literal": "Ruslan Salakhutdinov"
      },
      {
        "literal": "Daniel Fried"
      }
    ],
    "citation-key": "arxiv_2606_01533",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "acc6e8af676b7de5393469d379746e674ccd662f570399622d0d5b1b0e882939",
        "submitted_at": "2026-06-01T01:29:36Z",
        "updated_at": "2026-06-01T01:29:36Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2606.01533v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.01533",
      "catalog_id": "arxiv:2606.01533",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-01",
      "identifiers": {
        "arxiv": "2606.01533"
      },
      "record_updated_at": "2026-06-01"
    },
    "genre": "preprint",
    "id": "arxiv:2606.01533",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          1
        ]
      ]
    },
    "note": "First published: 2026-06-01; Recorded arXiv version: v1; Recorded version updated: 2026-06-01T01:29:36Z.",
    "title": "Multi-Agent Computer Use",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2606.03103v1",
    "archive": "arXiv",
    "archive_location": "2606.03103",
    "author": [
      {
        "literal": "Wenkai Wang"
      },
      {
        "literal": "Tao Xiong"
      },
      {
        "literal": "Jingchen Ni"
      },
      {
        "literal": "Yunpeng Bao"
      },
      {
        "literal": "Xiyun Li"
      },
      {
        "literal": "Tianqi Liu"
      },
      {
        "literal": "Hongcan Guo"
      },
      {
        "literal": "Zilong Huang"
      },
      {
        "literal": "Shengyu Zhang"
      }
    ],
    "citation-key": "arxiv_2606_03103",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "bf0fcafeb2d40e489ec80784a3541114b02c6a9077a330265d5c49775eca4582",
        "submitted_at": "2026-06-02T03:42:34Z",
        "updated_at": "2026-06-02T03:42:34Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2606.03103v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.03103",
      "catalog_id": "arxiv:2606.03103",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-02",
      "identifiers": {
        "arxiv": "2606.03103"
      },
      "record_updated_at": "2026-06-02"
    },
    "genre": "preprint",
    "id": "arxiv:2606.03103",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          2
        ]
      ]
    },
    "note": "First published: 2026-06-02; Recorded arXiv version: v1; Recorded version updated: 2026-06-02T03:42:34Z.",
    "title": "DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration",
    "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/2606.09426v3",
    "archive": "arXiv",
    "archive_location": "2606.09426",
    "author": [
      {
        "literal": "Wanli Li"
      },
      {
        "literal": "Bowen Zhou"
      },
      {
        "literal": "Yunyao Yu"
      },
      {
        "literal": "Zhou Xu"
      },
      {
        "literal": "Yifan Yang"
      },
      {
        "literal": "Dongsheng Li"
      },
      {
        "literal": "Caihua Shan"
      }
    ],
    "citation-key": "arxiv_2606_09426",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "73b751efd63d98fc81166a1a80cb0c162d68bf1ec4ecca0a1a1a7717ad62e680",
        "submitted_at": "2026-06-08T12:39:23Z",
        "updated_at": "2026-07-06T14:25:02Z",
        "version": 3,
        "versioned_url": "https://arxiv.org/abs/2606.09426v3"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.09426",
      "catalog_id": "arxiv:2606.09426",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-08",
      "identifiers": {
        "arxiv": "2606.09426"
      },
      "record_updated_at": "2026-07-06"
    },
    "genre": "preprint",
    "id": "arxiv:2606.09426",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          8
        ]
      ]
    },
    "note": "First published: 2026-06-08; Recorded arXiv version: v3; Recorded version updated: 2026-07-06T14:25:02Z.",
    "title": "WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces",
    "type": "article",
    "version": "3"
  },
  {
    "URL": "https://arxiv.org/abs/2606.11042v4",
    "archive": "arXiv",
    "archive_location": "2606.11042",
    "author": [
      {
        "literal": "Liya Zhu"
      },
      {
        "literal": "Jingzhe Ding"
      },
      {
        "literal": "Jian Zhang"
      },
      {
        "literal": "Jianbo Xue"
      },
      {
        "literal": "Shihao Liang"
      },
      {
        "literal": "Ge Zhang"
      },
      {
        "literal": "Yi Zhu"
      },
      {
        "literal": "Duju Zeng"
      },
      {
        "literal": "Xiang Gao"
      },
      {
        "literal": "Qingshui Gu"
      },
      {
        "literal": "Mailun Gao"
      },
      {
        "literal": "Huimin Che"
      },
      {
        "literal": "Yan Zhao"
      },
      {
        "literal": "Peiheng Zhou"
      },
      {
        "literal": "Haojun Wang"
      },
      {
        "literal": "Chaobo Xian"
      },
      {
        "literal": "Lili Le"
      },
      {
        "literal": "Chi Wu"
      },
      {
        "literal": "Yiwei Liu"
      },
      {
        "literal": "Shengda Long"
      },
      {
        "literal": "Jiale Yang"
      },
      {
        "literal": "Fangzhi Xu"
      },
      {
        "literal": "Sijin Wu"
      },
      {
        "literal": "Haodong Duan"
      },
      {
        "literal": "Chao He"
      },
      {
        "literal": "Zhaojian Li"
      },
      {
        "literal": "Minchao Wang"
      },
      {
        "literal": "Huan Zhou"
      },
      {
        "literal": "Jiani Hou"
      },
      {
        "literal": "Chuqian Yu"
      },
      {
        "literal": "Weiran Shi"
      },
      {
        "literal": "Hongwan Gao"
      },
      {
        "literal": "Jiamin Chen"
      },
      {
        "literal": "Guanhong Chen"
      },
      {
        "literal": "Tingqin Luo"
      },
      {
        "literal": "Kaiyuan Zhang"
      },
      {
        "literal": "Zhixin Yao"
      },
      {
        "literal": "Qing Hua"
      },
      {
        "literal": "Yuhao Jiang"
      },
      {
        "literal": "Jin Chen"
      },
      {
        "literal": "Pu Chen"
      },
      {
        "literal": "Zhenyu Hu"
      },
      {
        "literal": "Xingyu Li"
      },
      {
        "literal": "Zhengxuan Jiang"
      },
      {
        "literal": "Meng Cao"
      },
      {
        "literal": "Tianfeng Long"
      },
      {
        "literal": "Haozhe Wang"
      },
      {
        "literal": "Mingzhang Wang"
      },
      {
        "literal": "Yichen Zhang"
      },
      {
        "literal": "Yiming Dai"
      },
      {
        "literal": "Chenchen Zhang"
      },
      {
        "literal": "Jiaying Wang"
      },
      {
        "literal": "Xinying Liu"
      },
      {
        "literal": "Xingzu Liu"
      },
      {
        "literal": "Lingling Zhang"
      },
      {
        "literal": "Xinjie Chen"
      },
      {
        "literal": "Yujia Qin"
      },
      {
        "literal": "Wangchunshu Zhou"
      },
      {
        "literal": "Zhiyong Wu"
      },
      {
        "literal": "Yang Liu"
      },
      {
        "literal": "Jiaheng Liu"
      },
      {
        "literal": "Lei Zhang"
      },
      {
        "literal": "Shen Yan"
      },
      {
        "literal": "Wenhao Huang"
      },
      {
        "literal": "Zaiyuan Wang"
      },
      {
        "literal": "Xiaolong Chang"
      }
    ],
    "citation-key": "arxiv_2606_11042",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "037a3197137d27318320a3fd23fb5e606a1aa748133e57213cd02fd10aad4c4d",
        "submitted_at": "2026-06-09T16:10:16Z",
        "updated_at": "2026-07-17T12:22:12Z",
        "version": 4,
        "versioned_url": "https://arxiv.org/abs/2606.11042v4"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.11042",
      "catalog_id": "arxiv:2606.11042",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-09",
      "identifiers": {
        "arxiv": "2606.11042"
      },
      "record_updated_at": "2026-07-17"
    },
    "genre": "preprint",
    "id": "arxiv:2606.11042",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          9
        ]
      ]
    },
    "note": "First published: 2026-06-09; Recorded arXiv version: v4; Recorded version updated: 2026-07-17T12:22:12Z.",
    "title": "Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields",
    "type": "article",
    "version": "4"
  },
  {
    "URL": "https://arxiv.org/abs/2606.11078v1",
    "archive": "arXiv",
    "archive_location": "2606.11078",
    "author": [
      {
        "literal": "Jaewoo Lee"
      },
      {
        "literal": "Zaid Khan"
      },
      {
        "literal": "Archiki Prasad"
      },
      {
        "literal": "Justin Chih-Yao Chen"
      },
      {
        "literal": "Supriyo Chakraborty"
      },
      {
        "literal": "Kartik Balasubramaniam"
      },
      {
        "literal": "Sambit Sahu"
      },
      {
        "literal": "Elias Stengel-Eskin"
      },
      {
        "literal": "Hyunji Lee"
      },
      {
        "literal": "Mohit Bansal"
      }
    ],
    "citation-key": "arxiv_2606_11078",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "a8ed399c8b489a80c5313a00232d2ecca0fbc8228b1f56745c02d4fedb6f6908",
        "submitted_at": "2026-06-09T16:39:10Z",
        "updated_at": "2026-06-09T16:39:10Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2606.11078v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.11078",
      "catalog_id": "arxiv:2606.11078",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-09",
      "identifiers": {
        "arxiv": "2606.11078"
      },
      "record_updated_at": "2026-06-09"
    },
    "genre": "preprint",
    "id": "arxiv:2606.11078",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          9
        ]
      ]
    },
    "note": "First published: 2026-06-09; Recorded arXiv version: v1; Recorded version updated: 2026-06-09T16:39:10Z.",
    "title": "A History-Aware Visually Grounded Critic for Computer Use Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2606.16802v1",
    "archive": "arXiv",
    "archive_location": "2606.16802",
    "author": [
      {
        "literal": "Anqi Zou"
      },
      {
        "literal": "Han Deng"
      },
      {
        "literal": "Chengyu Zhang"
      },
      {
        "literal": "Junquan Hu"
      },
      {
        "literal": "Yu Wang"
      },
      {
        "literal": "Yuxiang Xing"
      },
      {
        "literal": "Aokai Zhang"
      },
      {
        "literal": "Hanling Zhang"
      },
      {
        "literal": "Zhaoyang Liu"
      },
      {
        "literal": "Ben Fei"
      },
      {
        "literal": "Zhihui Wang"
      },
      {
        "literal": "Wanli Ouyang"
      }
    ],
    "citation-key": "arxiv_2606_16802",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "7487f31097bc8de90dfbe836051d47f407c26e31a42bd751bedfd38cf4f1742c",
        "submitted_at": "2026-06-15T14:42:33Z",
        "updated_at": "2026-06-15T14:42:33Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2606.16802v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.16802",
      "catalog_id": "arxiv:2606.16802",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-15",
      "identifiers": {
        "arxiv": "2606.16802"
      },
      "record_updated_at": "2026-06-15"
    },
    "genre": "preprint",
    "id": "arxiv:2606.16802",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          15
        ]
      ]
    },
    "note": "First published: 2026-06-15; Recorded arXiv version: v1; Recorded version updated: 2026-06-15T14:42:33Z.",
    "title": "LabOSBench: Benchmarking Computer Use Agents for Scientific Instrument Control",
    "type": "article",
    "version": "1"
  },
  {
    "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/2606.19926v1",
    "archive": "arXiv",
    "archive_location": "2606.19926",
    "author": [
      {
        "literal": "Guangyi Liu"
      },
      {
        "literal": "Gao Wu"
      },
      {
        "literal": "Congxiao Liu"
      },
      {
        "literal": "Pengxiang Zhao"
      },
      {
        "literal": "Liang Liu"
      },
      {
        "literal": "Mading Li"
      },
      {
        "literal": "Qi Zhang"
      },
      {
        "literal": "Mengyan Wang"
      },
      {
        "literal": "Liang Guo"
      },
      {
        "literal": "Yong Liu"
      }
    ],
    "citation-key": "arxiv_2606_19926",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "cbbb1bd57057e465ce9d991d3f6e2bb52112fc133a5846fc8cb6ce51eddc2121",
        "submitted_at": "2026-06-18T08:26:09Z",
        "updated_at": "2026-06-18T08:26:09Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2606.19926v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.19926",
      "catalog_id": "arxiv:2606.19926",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-18",
      "identifiers": {
        "arxiv": "2606.19926"
      },
      "record_updated_at": "2026-06-18"
    },
    "genre": "preprint",
    "id": "arxiv:2606.19926",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          18
        ]
      ]
    },
    "note": "First published: 2026-06-18; Recorded arXiv version: v1; Recorded version updated: 2026-06-18T08:26:09Z.",
    "title": "MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2606.21654v2",
    "archive": "arXiv",
    "archive_location": "2606.21654",
    "author": [
      {
        "literal": "Vincent Siu"
      },
      {
        "literal": "Manasi Sharma"
      },
      {
        "literal": "Dawn Song"
      },
      {
        "literal": "Daniel Yue Zhang"
      },
      {
        "literal": "Chenguang Wang"
      },
      {
        "literal": "Ying Liu"
      }
    ],
    "citation-key": "arxiv_2606_21654",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "69e668a9491a31e8d8849bab8cc63eede9878fff10ccb0ae0a211610e90819b3",
        "submitted_at": "2026-06-19T18:00:14Z",
        "updated_at": "2026-08-19T17:29:04Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2606.21654v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.21654",
      "catalog_id": "arxiv:2606.21654",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-19",
      "identifiers": {
        "arxiv": "2606.21654"
      },
      "record_updated_at": "2026-08-19"
    },
    "genre": "preprint",
    "id": "arxiv:2606.21654",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          19
        ]
      ]
    },
    "note": "First published: 2026-06-19; Recorded arXiv version: v2; Recorded version updated: 2026-08-19T17:29:04Z.",
    "title": "ChainWorld: Composing Long-Horizon Desktop Workloads from Atomic OSWorld Tasks",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2606.22948v1",
    "archive": "arXiv",
    "archive_location": "2606.22948",
    "author": [
      {
        "literal": "Yincheng Zhou"
      },
      {
        "literal": "Athena Zhuoming Zhong"
      },
      {
        "literal": "Shijie Zhang"
      },
      {
        "literal": "Kevin Zhang"
      },
      {
        "literal": "Teresa Xiaotao Shang"
      },
      {
        "literal": "Shanghang Zhang"
      }
    ],
    "citation-key": "arxiv_2606_22948",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "fbd8892e06a5e847c16aa3101b98b3d669a783b84ee8e3d4d4d810754914028b",
        "submitted_at": "2026-06-22T07:28:55Z",
        "updated_at": "2026-06-22T07:28:55Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2606.22948v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.22948",
      "catalog_id": "arxiv:2606.22948",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-22",
      "identifiers": {
        "arxiv": "2606.22948"
      },
      "record_updated_at": "2026-06-22"
    },
    "genre": "preprint",
    "id": "arxiv:2606.22948",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          22
        ]
      ]
    },
    "note": "First published: 2026-06-22; Recorded arXiv version: v1; Recorded version updated: 2026-06-22T07:28:55Z.",
    "title": "ENVS: Environment-Native Verified Search for Long-Horizon GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2606.29537v2",
    "archive": "arXiv",
    "archive_location": "2606.29537",
    "author": [
      {
        "literal": "Mengqi Yuan"
      },
      {
        "literal": "Zilong Zhou"
      },
      {
        "literal": "Xinzhuang Xiong"
      },
      {
        "literal": "Weiming Wu"
      },
      {
        "literal": "Jiayang Sun"
      },
      {
        "literal": "Jiamin Song"
      },
      {
        "literal": "Kaiqian Cui"
      },
      {
        "literal": "Bowen Wang"
      },
      {
        "literal": "Haoyuan Wu"
      },
      {
        "literal": "Yitong Li"
      },
      {
        "literal": "Dunjie Lu"
      },
      {
        "literal": "Haikong Lu"
      },
      {
        "literal": "Qi Zhen"
      },
      {
        "literal": "Xinyuan Wang"
      },
      {
        "literal": "Jiaqi Deng"
      },
      {
        "literal": "Yuhao Yang"
      },
      {
        "literal": "Cheng Chen"
      },
      {
        "literal": "Boyuan Zheng"
      },
      {
        "literal": "Alex Su"
      },
      {
        "literal": "Xiao Yu"
      },
      {
        "literal": "Hao Zou"
      },
      {
        "literal": "Saaket Agashe"
      },
      {
        "literal": "Xing Han Lu"
      },
      {
        "literal": "Manpreet Kaur"
      },
      {
        "literal": "Zhengyang Qi"
      },
      {
        "literal": "Vincent Sunn Chen"
      },
      {
        "literal": "Frederic Sala"
      },
      {
        "literal": "Dayiheng Liu"
      },
      {
        "literal": "Junyang Lin"
      },
      {
        "literal": "Zhou Yu"
      },
      {
        "literal": "Yu Su"
      },
      {
        "literal": "Siva Reddy"
      },
      {
        "literal": "Xin Eric Wang"
      },
      {
        "literal": "Peng Qi"
      },
      {
        "literal": "Tianbao Xie"
      },
      {
        "literal": "Tao Yu"
      }
    ],
    "citation-key": "arxiv_2606_29537",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "03035fcbc6cd3e6bf40f244870fb35694ba985ff7f809da66e2a376cbf99d66b",
        "submitted_at": "2026-06-28T17:59:17Z",
        "updated_at": "2026-07-13T10:30:17Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2606.29537v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2606.29537",
      "catalog_id": "arxiv:2606.29537",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-06-28",
      "identifiers": {
        "arxiv": "2606.29537"
      },
      "record_updated_at": "2026-07-13"
    },
    "genre": "preprint",
    "id": "arxiv:2606.29537",
    "issued": {
      "date-parts": [
        [
          2026,
          6,
          28
        ]
      ]
    },
    "note": "First published: 2026-06-28; Recorded arXiv version: v2; Recorded version updated: 2026-07-13T10:30:17Z.",
    "title": "OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2607.09773v2",
    "archive": "arXiv",
    "archive_location": "2607.09773",
    "author": [
      {
        "literal": "Mianqiu Huang"
      },
      {
        "literal": "Taofeng Xue"
      },
      {
        "literal": "Chong Peng"
      },
      {
        "literal": "Jinrui Ding"
      },
      {
        "literal": "Jie Yang"
      },
      {
        "literal": "Sicheng Fan"
      },
      {
        "literal": "Jiale Hong"
      },
      {
        "literal": "Yufei Gao"
      },
      {
        "literal": "Xiaocheng Zhang"
      },
      {
        "literal": "Linsen Guo"
      },
      {
        "literal": "Xin Yang"
      },
      {
        "literal": "Dengchang Zhao"
      },
      {
        "literal": "Yuchen Xie"
      },
      {
        "literal": "Peng Pei"
      },
      {
        "literal": "Xunliang Xie"
      },
      {
        "literal": "Xipeng Qiu"
      }
    ],
    "citation-key": "arxiv_2607_09773",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "53c254c53a834d4f28bb4b65317121f5c46f5dd6985d03a30f1cc1f0fa78707d",
        "submitted_at": "2026-07-07T16:36:25Z",
        "updated_at": "2026-09-04T15:47:10Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2607.09773v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2607.09773",
      "catalog_id": "arxiv:2607.09773",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-07-07",
      "identifiers": {
        "arxiv": "2607.09773"
      },
      "record_updated_at": "2026-09-04"
    },
    "genre": "preprint",
    "id": "arxiv:2607.09773",
    "issued": {
      "date-parts": [
        [
          2026,
          7,
          7
        ]
      ]
    },
    "note": "First published: 2026-07-07; Recorded arXiv version: v2; Recorded version updated: 2026-09-04T15:47:10Z.",
    "title": "EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2607.10608v1",
    "archive": "arXiv",
    "archive_location": "2607.10608",
    "author": [
      {
        "literal": "Yixiong Chen"
      },
      {
        "literal": "Xinyi Bai"
      },
      {
        "literal": "Alan Yuille"
      }
    ],
    "citation-key": "arxiv_2607_10608",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "0473ced7881ed2007aa49c2767860c33719d5bf1c798dfe4771a4061b13d655e",
        "submitted_at": "2026-07-12T07:05:31Z",
        "updated_at": "2026-07-12T07:05:31Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2607.10608v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2607.10608",
      "catalog_id": "arxiv:2607.10608",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-07-12",
      "identifiers": {
        "arxiv": "2607.10608"
      },
      "record_updated_at": "2026-07-12"
    },
    "genre": "preprint",
    "id": "arxiv:2607.10608",
    "issued": {
      "date-parts": [
        [
          2026,
          7,
          12
        ]
      ]
    },
    "note": "First published: 2026-07-12; Recorded arXiv version: v1; Recorded version updated: 2026-07-12T07:05:31Z.",
    "title": "The Compliance Trap: Diagnosing How AI Agents Consume Conflicting Memory",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2607.11388v1",
    "archive": "arXiv",
    "archive_location": "2607.11388",
    "author": [
      {
        "literal": "Wenyi Wu"
      },
      {
        "literal": "Sibo Zhu"
      },
      {
        "literal": "Kun Zhou"
      },
      {
        "literal": "Aayush Salvi"
      },
      {
        "literal": "Zixuan Song"
      },
      {
        "literal": "Biwei Huang"
      }
    ],
    "citation-key": "arxiv_2607_11388",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "40daa1b180a0c2eaba7b907a0f61b8dd8819cb3033b9da118162330d97cfecf7",
        "submitted_at": "2026-07-13T10:48:25Z",
        "updated_at": "2026-07-13T10:48:25Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2607.11388v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2607.11388",
      "catalog_id": "arxiv:2607.11388",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-07-13",
      "identifiers": {
        "arxiv": "2607.11388"
      },
      "record_updated_at": "2026-07-13"
    },
    "genre": "preprint",
    "id": "arxiv:2607.11388",
    "issued": {
      "date-parts": [
        [
          2026,
          7,
          13
        ]
      ]
    },
    "note": "First published: 2026-07-13; Recorded arXiv version: v1; Recorded version updated: 2026-07-13T10:48:25Z.",
    "title": "StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2607.17527v1",
    "archive": "arXiv",
    "archive_location": "2607.17527",
    "author": [
      {
        "literal": "Ruei-Che Chang"
      },
      {
        "literal": "Wenqian Xu"
      },
      {
        "literal": "Dingzeyu Li"
      },
      {
        "literal": "Bryan Wang"
      },
      {
        "literal": "Anhong Guo"
      }
    ],
    "citation-key": "arxiv_2607_17527",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "2069acf693e0dced49d0e10e21bf9fe28b99f50f1b932837f16137e0d3170a80",
        "submitted_at": "2026-07-20T04:03:38Z",
        "updated_at": "2026-07-20T04:03:38Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2607.17527v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2607.17527",
      "catalog_id": "arxiv:2607.17527",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-07-20",
      "identifiers": {
        "arxiv": "2607.17527"
      },
      "record_updated_at": "2026-07-20"
    },
    "genre": "preprint",
    "id": "arxiv:2607.17527",
    "issued": {
      "date-parts": [
        [
          2026,
          7,
          20
        ]
      ]
    },
    "note": "First published: 2026-07-20; Recorded arXiv version: v1; Recorded version updated: 2026-07-20T04:03:38Z.",
    "title": "Sidekick: Designing Communication for Effective Multitasking with Computer Use Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2607.18046v2",
    "archive": "arXiv",
    "archive_location": "2607.18046",
    "author": [
      {
        "literal": "Zhuohang Fan"
      },
      {
        "literal": "Beichen Zhang"
      },
      {
        "literal": "Yuanfa Li"
      },
      {
        "literal": "Changqiao Wu"
      },
      {
        "literal": "Wei Liu"
      },
      {
        "literal": "Jian Luan"
      },
      {
        "literal": "Weigang Zhang"
      }
    ],
    "citation-key": "arxiv_2607_18046",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "b85b453a688543477d31a940f9d1da2857b2cb7a8cb9eea91a39a3a2b8a1e1c7",
        "submitted_at": "2026-07-20T15:16:59Z",
        "updated_at": "2026-08-18T02:32:56Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2607.18046v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2607.18046",
      "catalog_id": "arxiv:2607.18046",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-07-20",
      "identifiers": {
        "arxiv": "2607.18046"
      },
      "record_updated_at": "2026-08-18"
    },
    "genre": "preprint",
    "id": "arxiv:2607.18046",
    "issued": {
      "date-parts": [
        [
          2026,
          7,
          20
        ]
      ]
    },
    "note": "First published: 2026-07-20; Recorded arXiv version: v2; Recorded version updated: 2026-08-18T02:32:56Z.",
    "title": "SEE: Structure-aware Exploring & Exploiting for Long-horizon GUI Agent Trajectory Synthesis",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2607.22689v1",
    "archive": "arXiv",
    "archive_location": "2607.22689",
    "author": [
      {
        "literal": "Zedong Yu"
      },
      {
        "literal": "Qianxing Li"
      },
      {
        "literal": "Zhi Gao"
      },
      {
        "literal": "Liuyu Xiang"
      },
      {
        "literal": "Chenrui Shi"
      },
      {
        "literal": "Yang Liu"
      },
      {
        "literal": "Huiming Wu"
      },
      {
        "literal": "Yujie Wei"
      },
      {
        "literal": "Yuhao Fei"
      },
      {
        "literal": "Yubo Fu"
      },
      {
        "literal": "Zhaofeng He"
      }
    ],
    "citation-key": "arxiv_2607_22689",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "078ff9a56b769923d15a98581685a3e2f47aac7d898ea731999cabaec3918fa7",
        "submitted_at": "2026-07-17T12:48:03Z",
        "updated_at": "2026-07-17T12:48:03Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2607.22689v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2607.22689",
      "catalog_id": "arxiv:2607.22689",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-07-17",
      "identifiers": {
        "arxiv": "2607.22689"
      },
      "record_updated_at": "2026-07-17"
    },
    "genre": "preprint",
    "id": "arxiv:2607.22689",
    "issued": {
      "date-parts": [
        [
          2026,
          7,
          17
        ]
      ]
    },
    "note": "First published: 2026-07-17; Recorded arXiv version: v1; Recorded version updated: 2026-07-17T12:48:03Z.",
    "title": "Beyond Sequential Interaction: Benchmarking Parallel Execution and Coordination for GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2607.22798v1",
    "archive": "arXiv",
    "archive_location": "2607.22798",
    "author": [
      {
        "literal": "Yan Yang"
      },
      {
        "literal": "Xiangru Jian"
      },
      {
        "literal": "Ziyang Luo"
      },
      {
        "literal": "Zirui Zhao"
      },
      {
        "literal": "Yutong Dai"
      },
      {
        "literal": "Ziji Shi"
      },
      {
        "literal": "Hanshu Yan"
      },
      {
        "literal": "Jun Hao Liew"
      },
      {
        "literal": "Silvio Savarese"
      },
      {
        "literal": "Junnan Li"
      }
    ],
    "citation-key": "arxiv_2607_22798",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "a010fbef09d8359550cf156bf0dcba873f25a0d6fb8f118d53bf6e23715cf203",
        "submitted_at": "2026-07-24T14:17:03Z",
        "updated_at": "2026-07-24T14:17:03Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2607.22798v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2607.22798",
      "catalog_id": "arxiv:2607.22798",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-07-24",
      "identifiers": {
        "arxiv": "2607.22798"
      },
      "record_updated_at": "2026-07-24"
    },
    "genre": "preprint",
    "id": "arxiv:2607.22798",
    "issued": {
      "date-parts": [
        [
          2026,
          7,
          24
        ]
      ]
    },
    "note": "First published: 2026-07-24; Recorded arXiv version: v1; Recorded version updated: 2026-07-24T14:17:03Z.",
    "title": "StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2607.28227v1",
    "archive": "arXiv",
    "archive_location": "2607.28227",
    "author": [
      {
        "literal": "Hanzhang Zhou"
      },
      {
        "literal": "Panrong Tong"
      },
      {
        "literal": "Xu Zhang"
      },
      {
        "literal": "Quyu Kong"
      },
      {
        "literal": "Chenglin Cai"
      },
      {
        "literal": "Tianyu Xia"
      },
      {
        "literal": "Gongjie Zhang"
      },
      {
        "literal": "Jianan Zhang"
      },
      {
        "literal": "Long Li"
      },
      {
        "literal": "Long Chen"
      },
      {
        "literal": "Lei Wang"
      },
      {
        "literal": "Gaole Dai"
      },
      {
        "literal": "Pengxiang Li"
      },
      {
        "literal": "Liangyu Chen"
      },
      {
        "literal": "Yue Wang"
      },
      {
        "literal": "Steven Hoi"
      }
    ],
    "citation-key": "arxiv_2607_28227",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "52fb1b49501132f1dbe3564daa02cca22a93fc8d7c28dec8ee6070a23889574a",
        "submitted_at": "2026-07-30T13:58:41Z",
        "updated_at": "2026-07-30T13:58:41Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2607.28227v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2607.28227",
      "catalog_id": "arxiv:2607.28227",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-07-30",
      "identifiers": {
        "arxiv": "2607.28227"
      },
      "record_updated_at": "2026-07-30"
    },
    "genre": "preprint",
    "id": "arxiv:2607.28227",
    "issued": {
      "date-parts": [
        [
          2026,
          7,
          30
        ]
      ]
    },
    "note": "First published: 2026-07-30; Recorded arXiv version: v1; Recorded version updated: 2026-07-30T13:58:41Z.",
    "title": "Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2608.02352v1",
    "archive": "arXiv",
    "archive_location": "2608.02352",
    "author": [
      {
        "literal": "Dunjie Lu"
      },
      {
        "literal": "Shuai Bai"
      },
      {
        "literal": "Tianyi Bai"
      },
      {
        "literal": "Sicheng Fan"
      },
      {
        "literal": "Chang Gao"
      },
      {
        "literal": "Jian Guan"
      },
      {
        "literal": "Feng Hu"
      },
      {
        "literal": "Mianqiu Huang"
      },
      {
        "literal": "Xingyang Huang"
      },
      {
        "literal": "Yizhen Jiang"
      },
      {
        "literal": "Yuheng Jing"
      },
      {
        "literal": "Dehui Kong"
      },
      {
        "literal": "Ning Li"
      },
      {
        "literal": "Dayiheng Liu"
      },
      {
        "literal": "Shixuan Liu"
      },
      {
        "literal": "Zheng Liu"
      },
      {
        "literal": "Que Shen"
      },
      {
        "literal": "Bowen Wang"
      },
      {
        "literal": "Junli Wang"
      },
      {
        "literal": "Chencan Wu"
      },
      {
        "literal": "Rui Xie"
      },
      {
        "literal": "Tianbao Xie"
      },
      {
        "literal": "Zhihui Xie"
      },
      {
        "literal": "Haiyang Xu"
      },
      {
        "literal": "An Yang"
      },
      {
        "literal": "Tao Yu"
      },
      {
        "literal": "Wenzhen Yuan"
      },
      {
        "literal": "Xi Zhang"
      },
      {
        "literal": "Zhenru Zhang"
      },
      {
        "literal": "Mingkang Zhu"
      },
      {
        "literal": "Zhaoqing Zhu"
      },
      {
        "literal": "Yizhong Cao"
      },
      {
        "literal": "Kai Dang"
      },
      {
        "literal": "Binyuan Hui"
      },
      {
        "literal": "Kaixin Li"
      },
      {
        "literal": "Junyang Lin"
      },
      {
        "literal": "Haiquan Wang"
      },
      {
        "literal": "Zekun Wang"
      },
      {
        "literal": "Yiheng Xu"
      },
      {
        "literal": "Fan Yan"
      },
      {
        "literal": "Mengqi Yuan"
      },
      {
        "literal": "Danyang Zhang"
      },
      {
        "literal": "Jiajun Zhang"
      },
      {
        "literal": "Zhipeng Zhang"
      },
      {
        "literal": "Fan Zhou"
      },
      {
        "literal": "Fan Zhou"
      }
    ],
    "citation-key": "arxiv_2608_02352",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "26a61ccfdddb5cdc2da2b14d29ae8d4098544fea4e9458126f2a49c28418c4f0",
        "submitted_at": "2026-08-03T15:04:20Z",
        "updated_at": "2026-08-03T15:04:20Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2608.02352v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2608.02352",
      "catalog_id": "arxiv:2608.02352",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-08-03",
      "identifiers": {
        "arxiv": "2608.02352"
      },
      "record_updated_at": "2026-08-03"
    },
    "genre": "preprint",
    "id": "arxiv:2608.02352",
    "issued": {
      "date-parts": [
        [
          2026,
          8,
          3
        ]
      ]
    },
    "note": "First published: 2026-08-03; Recorded arXiv version: v1; Recorded version updated: 2026-08-03T15:04:20Z.",
    "title": "Qwen-CUA: Native Computer Use for (almost) Everything",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2608.10366v1",
    "archive": "arXiv",
    "archive_location": "2608.10366",
    "author": [
      {
        "literal": "Mizanur Rahman"
      },
      {
        "literal": "Mohammed Saidul Islam"
      },
      {
        "literal": "Ridwan Mahbub"
      },
      {
        "literal": "Md Tahmid Rahman Laskar"
      },
      {
        "literal": "Shafiq Joty"
      },
      {
        "literal": "Enamul Hoque Prince"
      }
    ],
    "citation-key": "arxiv_2608_10366",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "e1089e57e0f0146f29a4a411c5c6f72da3c9f45be223fbbc5c9630315be6a680",
        "submitted_at": "2026-08-11T01:45:56Z",
        "updated_at": "2026-08-11T01:45:56Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2608.10366v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2608.10366",
      "catalog_id": "arxiv:2608.10366",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-08-11",
      "identifiers": {
        "arxiv": "2608.10366"
      },
      "record_updated_at": "2026-08-11"
    },
    "genre": "preprint",
    "id": "arxiv:2608.10366",
    "issued": {
      "date-parts": [
        [
          2026,
          8,
          11
        ]
      ]
    },
    "note": "First published: 2026-08-11; Recorded arXiv version: v1; Recorded version updated: 2026-08-11T01:45:56Z.",
    "title": "DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2608.15930v1",
    "archive": "arXiv",
    "archive_location": "2608.15930",
    "author": [
      {
        "literal": "Zihan Ding"
      },
      {
        "literal": "Longxu Dou"
      },
      {
        "literal": "Qi Gao"
      },
      {
        "literal": "Xiangwu Guo"
      },
      {
        "literal": "Shengchao Hu"
      },
      {
        "literal": "Zilong Huang"
      },
      {
        "literal": "Zihang Jiang"
      },
      {
        "literal": "Lei Ke"
      },
      {
        "literal": "Mengcheng Lan"
      },
      {
        "literal": "Weixian Lei"
      },
      {
        "literal": "Hanxuan Li"
      },
      {
        "literal": "Honglin Li"
      },
      {
        "literal": "Xiyun Li"
      },
      {
        "literal": "Zaitang Li"
      },
      {
        "literal": "Leowei Liang"
      },
      {
        "literal": "Xin Luo"
      },
      {
        "literal": "Haozhe Ma"
      },
      {
        "literal": "Jiayi Mao"
      },
      {
        "literal": "Zhoujie Pan"
      },
      {
        "literal": "Can Qin"
      },
      {
        "literal": "Tianyuan Qu"
      },
      {
        "literal": "Weiqi Wang"
      },
      {
        "literal": "Wenkai Wang"
      },
      {
        "literal": "Yonglin Wang"
      },
      {
        "literal": "Yuxin Wang"
      },
      {
        "literal": "Chenxu Wu"
      },
      {
        "literal": "Yingchen Yu"
      },
      {
        "literal": "Chenyu Zhang"
      },
      {
        "literal": "Yuhao Zheng"
      }
    ],
    "citation-key": "arxiv_2608_15930",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "efe635792c696bca73c9a436be67d8528582fb239d4d4f8d3de531219b1f4f8e",
        "submitted_at": "2026-08-16T20:59:59Z",
        "updated_at": "2026-08-16T20:59:59Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2608.15930v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2608.15930",
      "catalog_id": "arxiv:2608.15930",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-08-16",
      "identifiers": {
        "arxiv": "2608.15930"
      },
      "record_updated_at": "2026-08-16"
    },
    "genre": "preprint",
    "id": "arxiv:2608.15930",
    "issued": {
      "date-parts": [
        [
          2026,
          8,
          16
        ]
      ]
    },
    "note": "First published: 2026-08-16; Recorded arXiv version: v1; Recorded version updated: 2026-08-16T20:59:59Z.",
    "title": "UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2608.17319v1",
    "archive": "arXiv",
    "archive_location": "2608.17319",
    "author": [
      {
        "literal": "AIMAE Team"
      },
      {
        "literal": "Tianxiang Chen"
      },
      {
        "literal": "Yan Cheng"
      },
      {
        "literal": "Zhangye Han"
      },
      {
        "literal": "Xiaowei Li"
      },
      {
        "literal": "Chang Liu"
      },
      {
        "literal": "Cheng Liu"
      },
      {
        "literal": "Zhongqiang Ma"
      },
      {
        "literal": "Long Peng"
      },
      {
        "literal": "Xiaobing Tu"
      },
      {
        "literal": "Yinggui Wang"
      },
      {
        "literal": "Hongliang Wei"
      },
      {
        "literal": "Chen Wu"
      },
      {
        "literal": "Daiping Xin"
      },
      {
        "literal": "Kunyu Zhou"
      },
      {
        "literal": "Pengyang Zhou"
      },
      {
        "literal": "Peiyuan Chen"
      },
      {
        "literal": "Ziyuan Chen"
      },
      {
        "literal": "Yutao Deng"
      },
      {
        "literal": "Chunyu Dong"
      },
      {
        "literal": "Xiangyu Fu"
      },
      {
        "literal": "Yicheng Feng"
      },
      {
        "literal": "Ruian He"
      },
      {
        "literal": "Haochen Li"
      },
      {
        "literal": "Miancan Liu"
      },
      {
        "literal": "Zhengqin Liu"
      },
      {
        "literal": "Wei Peng"
      },
      {
        "literal": "Jinkui Ren"
      },
      {
        "literal": "Haoyu Tan"
      },
      {
        "literal": "Dong Xiao"
      },
      {
        "literal": "Rongkun Xue"
      },
      {
        "literal": "Shujian Yang"
      },
      {
        "literal": "Xianhang Ye"
      },
      {
        "literal": "Ziqi Yuan"
      },
      {
        "literal": "Ziyang Yu"
      },
      {
        "literal": "Linghan Zhang"
      },
      {
        "literal": "Xiantao Zhang"
      },
      {
        "literal": "Xuanpu Zhao"
      },
      {
        "literal": "Yinan Zhao"
      },
      {
        "literal": "Zhenghui Zhao"
      },
      {
        "literal": "Bin Zhu"
      },
      {
        "literal": "Likai Zou"
      }
    ],
    "citation-key": "arxiv_2608_17319",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "474187aaa79165dc8652eec1e2af6b1733b2ee37b3cd125c89ff0defcaf2e193",
        "submitted_at": "2026-08-18T03:23:31Z",
        "updated_at": "2026-08-18T03:23:31Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2608.17319v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2608.17319",
      "catalog_id": "arxiv:2608.17319",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-08-18",
      "identifiers": {
        "arxiv": "2608.17319"
      },
      "record_updated_at": "2026-08-18"
    },
    "genre": "preprint",
    "id": "arxiv:2608.17319",
    "issued": {
      "date-parts": [
        [
          2026,
          8,
          18
        ]
      ]
    },
    "note": "First published: 2026-08-18; Recorded arXiv version: v1; Recorded version updated: 2026-08-18T03:23:31Z.",
    "title": "Wuying-Browser-Agent: Real-World Centric Fundamental Long-Horizon Browser Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2608.22577v2",
    "archive": "arXiv",
    "archive_location": "2608.22577",
    "author": [
      {
        "literal": "Jiaxuan Luo"
      },
      {
        "literal": "Zhanfeng Liao"
      },
      {
        "literal": "Jiayao Teng"
      },
      {
        "literal": "Yuan Wang"
      }
    ],
    "citation-key": "arxiv_2608_22577",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "2ea33a82ab7543a64b60ee3024c6f3e39f88b4e3f06eff94f8c790c56cf76715",
        "submitted_at": "2026-08-23T20:04:21Z",
        "updated_at": "2026-08-25T04:24:36Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2608.22577v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2608.22577",
      "catalog_id": "arxiv:2608.22577",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-08-23",
      "identifiers": {
        "arxiv": "2608.22577"
      },
      "record_updated_at": "2026-08-25"
    },
    "genre": "preprint",
    "id": "arxiv:2608.22577",
    "issued": {
      "date-parts": [
        [
          2026,
          8,
          23
        ]
      ]
    },
    "note": "First published: 2026-08-23; Recorded arXiv version: v2; Recorded version updated: 2026-08-25T04:24:36Z.",
    "title": "CausalCache: Conditional High-Fidelity Restoration for Long-Horizon GUI Agents",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2609.00048v1",
    "archive": "arXiv",
    "archive_location": "2609.00048",
    "author": [
      {
        "literal": "Lin Fu"
      },
      {
        "literal": "Zheyuan Yang"
      },
      {
        "literal": "Tianhui Zhang"
      },
      {
        "literal": "Jinbiao Wei"
      },
      {
        "literal": "Guo Gan"
      },
      {
        "literal": "Boxu Liu"
      },
      {
        "literal": "Yilun Zhao"
      },
      {
        "literal": "Yu Rong"
      }
    ],
    "citation-key": "arxiv_2609_00048",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "dba8eb3f30a7e88ad973080d07fbf272f63400f4f8fa858d5f2657735ce093c0",
        "submitted_at": "2026-08-30T05:19:43Z",
        "updated_at": "2026-08-30T05:19:43Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2609.00048v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2609.00048",
      "catalog_id": "arxiv:2609.00048",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-08-30",
      "identifiers": {
        "arxiv": "2609.00048"
      },
      "record_updated_at": "2026-08-30"
    },
    "genre": "preprint",
    "id": "arxiv:2609.00048",
    "issued": {
      "date-parts": [
        [
          2026,
          8,
          30
        ]
      ]
    },
    "note": "First published: 2026-08-30; Recorded arXiv version: v1; Recorded version updated: 2026-08-30T05:19:43Z.",
    "title": "GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2609.10451v1",
    "archive": "arXiv",
    "archive_location": "2609.10451",
    "author": [
      {
        "literal": "Zixiang Chen"
      },
      {
        "literal": "Yuheng Lu"
      },
      {
        "literal": "Zihao Cheng"
      },
      {
        "literal": "Zeming Liu"
      },
      {
        "literal": "Jizeng Bai"
      },
      {
        "literal": "Ziye Huang"
      },
      {
        "literal": "Zhiyin Lin"
      },
      {
        "literal": "Zihan Li"
      },
      {
        "literal": "Yuhang Guo"
      },
      {
        "literal": "Yunhong Wang"
      },
      {
        "literal": "Haifeng Wang"
      }
    ],
    "citation-key": "arxiv_2609_10451",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "5ec17516bce87a8e349983acac14415a6ceeb12c167fce57aa37d6157cd3cd83",
        "submitted_at": "2026-09-09T16:59:59Z",
        "updated_at": "2026-09-09T16:59:59Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2609.10451v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2609.10451",
      "catalog_id": "arxiv:2609.10451",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-09-09",
      "identifiers": {
        "arxiv": "2609.10451"
      },
      "record_updated_at": "2026-09-09"
    },
    "genre": "preprint",
    "id": "arxiv:2609.10451",
    "issued": {
      "date-parts": [
        [
          2026,
          9,
          9
        ]
      ]
    },
    "note": "First published: 2026-09-09; Recorded arXiv version: v1; Recorded version updated: 2026-09-09T16:59:59Z.",
    "title": "JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2609.16251v2",
    "archive": "arXiv",
    "archive_location": "2609.16251",
    "author": [
      {
        "literal": "Zihan Dong"
      },
      {
        "literal": "Yuanzhe Liu"
      },
      {
        "literal": "Zhiyuan Ma"
      },
      {
        "literal": "Qishi Zhan"
      },
      {
        "literal": "Dehan Kong"
      },
      {
        "literal": "Guohao Li"
      },
      {
        "literal": "Kaixin Li"
      }
    ],
    "citation-key": "arxiv_2609_16251",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "0f5fd0a3024311f9aba44a2971c9c752ee2c38444139823746b90a7c9a6d5ed4",
        "submitted_at": "2026-09-14T19:19:05Z",
        "updated_at": "2026-09-21T14:30:34Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2609.16251v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2609.16251",
      "catalog_id": "arxiv:2609.16251",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-09-14",
      "identifiers": {
        "arxiv": "2609.16251"
      },
      "record_updated_at": "2026-09-21"
    },
    "genre": "preprint",
    "id": "arxiv:2609.16251",
    "issued": {
      "date-parts": [
        [
          2026,
          9,
          14
        ]
      ]
    },
    "note": "First published: 2026-09-14; Recorded arXiv version: v2; Recorded version updated: 2026-09-21T14:30:34Z.",
    "title": "CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2609.17653v1",
    "archive": "arXiv",
    "archive_location": "2609.17653",
    "author": [
      {
        "literal": "Bofan Chen"
      },
      {
        "literal": "Boxuan Zhang"
      },
      {
        "literal": "Fei Tang"
      },
      {
        "literal": "Zhengxi Lu"
      },
      {
        "literal": "Yong Du"
      },
      {
        "literal": "Tongbo Chen"
      },
      {
        "literal": "Weiming Lu"
      },
      {
        "literal": "Jun Xiao"
      },
      {
        "literal": "Yueting Zhuang"
      },
      {
        "literal": "Yongliang Shen"
      }
    ],
    "citation-key": "arxiv_2609_17653",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "975662f216cc9a6b89856d4457f2125b733620e80bfac1b6424775253071d2e6",
        "submitted_at": "2026-09-15T17:24:06Z",
        "updated_at": "2026-09-15T17:24:06Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2609.17653v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2609.17653",
      "catalog_id": "arxiv:2609.17653",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-09-15",
      "identifiers": {
        "arxiv": "2609.17653"
      },
      "record_updated_at": "2026-09-15"
    },
    "genre": "preprint",
    "id": "arxiv:2609.17653",
    "issued": {
      "date-parts": [
        [
          2026,
          9,
          15
        ]
      ]
    },
    "note": "First published: 2026-09-15; Recorded arXiv version: v1; Recorded version updated: 2026-09-15T17:24:06Z.",
    "title": "Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2609.30604v1",
    "archive": "arXiv",
    "archive_location": "2609.30604",
    "author": [
      {
        "literal": "Alexander Gill"
      },
      {
        "literal": "Md Farhan Ishmam"
      },
      {
        "literal": "Xuyen Nguyen"
      },
      {
        "literal": "Neha Bhat"
      },
      {
        "literal": "Parker Henry DeYoung"
      },
      {
        "literal": "Fateme Hashemi Chaleshtori"
      },
      {
        "literal": "Nathan Stringham"
      },
      {
        "literal": "Kenneth Marino"
      },
      {
        "literal": "Ana Marasović"
      }
    ],
    "citation-key": "arxiv_2609_30604",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "d6ed206d8f8fec53c03956fffcafec6b55d94a47fc705bbc8b77c832b76419e6",
        "submitted_at": "2026-09-24T22:36:10Z",
        "updated_at": "2026-09-24T22:36:10Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2609.30604v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2609.30604",
      "catalog_id": "arxiv:2609.30604",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-09-24",
      "identifiers": {
        "arxiv": "2609.30604"
      },
      "record_updated_at": "2026-09-24"
    },
    "genre": "preprint",
    "id": "arxiv:2609.30604",
    "issued": {
      "date-parts": [
        [
          2026,
          9,
          24
        ]
      ]
    },
    "note": "First published: 2026-09-24; Recorded arXiv version: v1; Recorded version updated: 2026-09-24T22:36:10Z.",
    "title": "The Hard Part Comes After Search: Benchmarking Web Agents on Synthesizing, Organizing, and Displaying Knowledge",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2609.34769v1",
    "archive": "arXiv",
    "archive_location": "2609.34769",
    "author": [
      {
        "literal": "Bingo Zhang"
      },
      {
        "literal": "Haochuan Lu"
      },
      {
        "literal": "Zongjie Li"
      },
      {
        "literal": "Genjian Li"
      },
      {
        "literal": "Ari Yu Zhang"
      },
      {
        "literal": "Chaozheng Wang"
      }
    ],
    "citation-key": "arxiv_2609_34769",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "f81fd07262dccf6783729e4336fbd77835f2fcdea030eef8dc2272e7ef82b8fc",
        "submitted_at": "2026-09-28T09:49:25Z",
        "updated_at": "2026-09-28T09:49:25Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2609.34769v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2609.34769",
      "catalog_id": "arxiv:2609.34769",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "adjacent",
      "first_published_at": "2026-09-28",
      "identifiers": {
        "arxiv": "2609.34769"
      },
      "record_updated_at": "2026-09-28"
    },
    "genre": "preprint",
    "id": "arxiv:2609.34769",
    "issued": {
      "date-parts": [
        [
          2026,
          9,
          28
        ]
      ]
    },
    "note": "First published: 2026-09-28; Recorded arXiv version: v1; Recorded version updated: 2026-09-28T09:49:25Z.",
    "title": "LongPuzzleBench: Evaluating GUI Agents on Long-Horizon Visual Puzzles",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2609.36923v1",
    "archive": "arXiv",
    "archive_location": "2609.36923",
    "author": [
      {
        "literal": "Bin Kang"
      },
      {
        "literal": "Jiarui Ouyang"
      },
      {
        "literal": "Li Jiang"
      },
      {
        "literal": "Bin Chen"
      },
      {
        "literal": "Zhuotao Tian"
      }
    ],
    "citation-key": "arxiv_2609_36923",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "e3af30198735ca9b9d192e15acbb7f8a37fe222fa2c0c1d2ccff448ef5e79f55",
        "submitted_at": "2026-09-29T07:41:34Z",
        "updated_at": "2026-09-29T07:41:34Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2609.36923v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2609.36923",
      "catalog_id": "arxiv:2609.36923",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-09-29",
      "identifiers": {
        "arxiv": "2609.36923"
      },
      "record_updated_at": "2026-09-29"
    },
    "genre": "preprint",
    "id": "arxiv:2609.36923",
    "issued": {
      "date-parts": [
        [
          2026,
          9,
          29
        ]
      ]
    },
    "note": "First published: 2026-09-29; Recorded arXiv version: v1; Recorded version updated: 2026-09-29T07:41:34Z.",
    "title": "PrecogUI: Proactive GUI Agents via Pre-cognitive Simulation and Experience Retrieval",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2610.07118v1",
    "archive": "arXiv",
    "archive_location": "2610.07118",
    "author": [
      {
        "literal": "Chinmay Savadikar"
      },
      {
        "literal": "Zhaoyu Zhang"
      },
      {
        "literal": "Mingyu Zhao"
      },
      {
        "literal": "Shuang Xie"
      },
      {
        "literal": "Han Li"
      },
      {
        "literal": "Tianfu Wu"
      },
      {
        "literal": "Lingyun Wang"
      }
    ],
    "citation-key": "arxiv_2610_07118",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "4890856d5961395a9ac8c83c60b988da4adeaab1d99edd511e4046e4f99fd25d",
        "submitted_at": "2026-10-05T17:11:07Z",
        "updated_at": "2026-10-05T17:11:07Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2610.07118v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2610.07118",
      "catalog_id": "arxiv:2610.07118",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-10-05",
      "identifiers": {
        "arxiv": "2610.07118"
      },
      "record_updated_at": "2026-10-05"
    },
    "genre": "preprint",
    "id": "arxiv:2610.07118",
    "issued": {
      "date-parts": [
        [
          2026,
          10,
          5
        ]
      ]
    },
    "note": "First published: 2026-10-05; Recorded arXiv version: v1; Recorded version updated: 2026-10-05T17:11:07Z.",
    "title": "AMBER: Training Long-Horizon Web Agents through Append-Only Memory",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2610.11050v1",
    "archive": "arXiv",
    "archive_location": "2610.11050",
    "author": [
      {
        "literal": "Xing Han Lù"
      },
      {
        "literal": "Dheeraj Vattikonda"
      },
      {
        "literal": "Sina Hajimiri"
      },
      {
        "literal": "Fatemeh Pesaran Zadeh"
      },
      {
        "literal": "Parishad BehnamGhader"
      },
      {
        "literal": "Ghazwa Darwiche"
      },
      {
        "literal": "Amirhossein Kazemnejad"
      },
      {
        "literal": "Christopher Pal"
      },
      {
        "literal": "Alexandre Drouin"
      },
      {
        "literal": "Siva Reddy"
      }
    ],
    "citation-key": "arxiv_2610_11050",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "37413f11bf8263f1516a8edca8c594227fcab104c0c767a7daa8eead9645ec34",
        "submitted_at": "2026-10-08T01:03:48Z",
        "updated_at": "2026-10-08T01:03:48Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2610.11050v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2610.11050",
      "catalog_id": "arxiv:2610.11050",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-10-08",
      "identifiers": {
        "arxiv": "2610.11050"
      },
      "record_updated_at": "2026-10-08"
    },
    "genre": "preprint",
    "id": "arxiv:2610.11050",
    "issued": {
      "date-parts": [
        [
          2026,
          10,
          8
        ]
      ]
    },
    "note": "First published: 2026-10-08; Recorded arXiv version: v1; Recorded version updated: 2026-10-08T01:03:48Z.",
    "title": "AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2610.17710v1",
    "archive": "arXiv",
    "archive_location": "2610.17710",
    "author": [
      {
        "literal": "Zirui Shang"
      },
      {
        "literal": "Yang Liu"
      },
      {
        "literal": "Xin Shu"
      },
      {
        "literal": "Zhi Gao"
      },
      {
        "literal": "Xinxiao Wu"
      },
      {
        "literal": "Lifeng Fan"
      }
    ],
    "citation-key": "arxiv_2610_17710",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "46ea5a1a350ccfcc12d22ab3783e05e3c580719962831561b01aeb3fcc6f6c28",
        "submitted_at": "2026-10-13T04:37:18Z",
        "updated_at": "2026-10-13T04:37:18Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2610.17710v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2610.17710",
      "catalog_id": "arxiv:2610.17710",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-10-13",
      "identifiers": {
        "arxiv": "2610.17710"
      },
      "record_updated_at": "2026-10-13"
    },
    "genre": "preprint",
    "id": "arxiv:2610.17710",
    "issued": {
      "date-parts": [
        [
          2026,
          10,
          13
        ]
      ]
    },
    "note": "First published: 2026-10-13; Recorded arXiv version: v1; Recorded version updated: 2026-10-13T04:37:18Z.",
    "title": "Adaptive-Group Process Rewards for GUI Agents",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2610.18067v1",
    "archive": "arXiv",
    "archive_location": "2610.18067",
    "author": [
      {
        "literal": "Hang He"
      },
      {
        "literal": "Linting Wang"
      },
      {
        "literal": "Guanming Liu"
      },
      {
        "literal": "Bo Mao"
      },
      {
        "literal": "Jinxiu Liu"
      },
      {
        "literal": "Yiran Suo"
      },
      {
        "literal": "Maosen Zhou"
      },
      {
        "literal": "Zhiheng Xi"
      },
      {
        "literal": "Guanting Dong"
      },
      {
        "literal": "Zhou Shao"
      },
      {
        "literal": "Rui Zheng"
      },
      {
        "literal": "Jie Zhou"
      },
      {
        "literal": "Chengcheng Wan"
      },
      {
        "literal": "Tao Gui"
      },
      {
        "literal": "Qi Zhang"
      },
      {
        "literal": "Xipeng Qiu"
      },
      {
        "literal": "Xuanjing Huang"
      }
    ],
    "citation-key": "arxiv_2610_18067",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "6add363f25f87ea1814c7b79ebf6b51f7431b3745a7d2d910960b78e2d97d13f",
        "submitted_at": "2026-10-13T09:52:02Z",
        "updated_at": "2026-10-13T09:52:02Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2610.18067v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2610.18067",
      "catalog_id": "arxiv:2610.18067",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-10-13",
      "identifiers": {
        "arxiv": "2610.18067"
      },
      "record_updated_at": "2026-10-13"
    },
    "genre": "preprint",
    "id": "arxiv:2610.18067",
    "issued": {
      "date-parts": [
        [
          2026,
          10,
          13
        ]
      ]
    },
    "note": "First published: 2026-10-13; Recorded arXiv version: v1; Recorded version updated: 2026-10-13T09:52:02Z.",
    "title": "WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2610.18784v2",
    "archive": "arXiv",
    "archive_location": "2610.18784",
    "author": [
      {
        "literal": "Yuchen Lu"
      },
      {
        "literal": "Julian McAuley"
      },
      {
        "literal": "Lei Zhang"
      }
    ],
    "citation-key": "arxiv_2610_18784",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "6f4a9b6fae506d4dd35798c1930d5df4ec7fc7a2c452ab8bd5a5714cf385d505",
        "submitted_at": "2026-10-13T17:35:27Z",
        "updated_at": "2026-10-14T04:46:42Z",
        "version": 2,
        "versioned_url": "https://arxiv.org/abs/2610.18784v2"
      },
      "canonical_source_url": "https://arxiv.org/abs/2610.18784",
      "catalog_id": "arxiv:2610.18784",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "adjacent",
      "first_published_at": "2026-10-13",
      "identifiers": {
        "arxiv": "2610.18784"
      },
      "record_updated_at": "2026-10-14"
    },
    "genre": "preprint",
    "id": "arxiv:2610.18784",
    "issued": {
      "date-parts": [
        [
          2026,
          10,
          13
        ]
      ]
    },
    "note": "First published: 2026-10-13; Recorded arXiv version: v2; Recorded version updated: 2026-10-14T04:46:42Z.",
    "title": "Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents",
    "type": "article",
    "version": "2"
  },
  {
    "URL": "https://arxiv.org/abs/2610.22408v1",
    "archive": "arXiv",
    "archive_location": "2610.22408",
    "author": [
      {
        "literal": "Tengda Guo"
      },
      {
        "literal": "Jiawang Hu"
      },
      {
        "literal": "Yifei Tao"
      },
      {
        "literal": "Yin Wang"
      },
      {
        "literal": "Haotian Hu"
      },
      {
        "literal": "Fanyi Wang"
      },
      {
        "literal": "Liujuan Tang"
      }
    ],
    "citation-key": "arxiv_2610_22408",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "025c7018c86ae4de79a659242070b2f91c5913333e9ecd4bd7fd357d13d27a34",
        "submitted_at": "2026-10-14T14:39:41Z",
        "updated_at": "2026-10-14T14:39:41Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2610.22408v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2610.22408",
      "catalog_id": "arxiv:2610.22408",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-10-14",
      "identifiers": {
        "arxiv": "2610.22408"
      },
      "record_updated_at": "2026-10-14"
    },
    "genre": "preprint",
    "id": "arxiv:2610.22408",
    "issued": {
      "date-parts": [
        [
          2026,
          10,
          14
        ]
      ]
    },
    "note": "First published: 2026-10-14; Recorded arXiv version: v1; Recorded version updated: 2026-10-14T14:39:41Z.",
    "title": "ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation",
    "type": "article",
    "version": "1"
  },
  {
    "URL": "https://arxiv.org/abs/2610.26828v1",
    "archive": "arXiv",
    "archive_location": "2610.26828",
    "author": [
      {
        "literal": "Zhaoyang Wang"
      },
      {
        "literal": "Qianhui Wu"
      },
      {
        "literal": "Haorui Wang"
      },
      {
        "literal": "Simon Yu"
      },
      {
        "literal": "Baolin Peng"
      },
      {
        "literal": "Canwen Xu"
      },
      {
        "literal": "Hao Cheng"
      },
      {
        "literal": "Wenlin Yao"
      },
      {
        "literal": "Boyi Liu"
      },
      {
        "literal": "Yite Wang"
      },
      {
        "literal": "Jianfeng Gao"
      },
      {
        "literal": "Huaxiu Yao"
      }
    ],
    "citation-key": "arxiv_2610_26828",
    "custom": {
      "arxiv_snapshot": {
        "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1",
        "abstract_sha256": "1f1ff33859352b61f017709fff91fd8e32f08636e9423fb044e7ca8e28f06905",
        "submitted_at": "2026-10-19T17:55:35Z",
        "updated_at": "2026-10-19T17:55:35Z",
        "version": 1,
        "versioned_url": "https://arxiv.org/abs/2610.26828v1"
      },
      "canonical_source_url": "https://arxiv.org/abs/2610.26828",
      "catalog_id": "arxiv:2610.26828",
      "catalog_kind": "paper",
      "catalog_review_status": "curated",
      "catalog_scope": "core",
      "first_published_at": "2026-10-19",
      "identifiers": {
        "arxiv": "2610.26828"
      },
      "record_updated_at": "2026-10-19"
    },
    "genre": "preprint",
    "id": "arxiv:2610.26828",
    "issued": {
      "date-parts": [
        [
          2026,
          10,
          19
        ]
      ]
    },
    "note": "First published: 2026-10-19; Recorded arXiv version: v1; Recorded version updated: 2026-10-19T17:55:35Z.",
    "title": "Agent World Model in the Wild: Computer-Use Agent Environment Synthesis",
    "type": "article",
    "version": "1"
  }
]