[ { "URL": "https://arxiv.org/abs/2407.15673v3", "archive": "arXiv", "archive_location": "2407.15673", "author": [ { "literal": "Segev Shlomov" }, { "literal": "Avi Yaeli" }, { "literal": "Sami Marreed" }, { "literal": "Sivan Schwartz" }, { "literal": "Netanel Eder" }, { "literal": "Offer Akrabi" }, { "literal": "Sergey Zeltyn" } ], "citation-key": "arxiv_2407_15673", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4caa87e0b88d9375a23ca412ed19b3806f67712ca4ac222a39746e08ee80b07d", "submitted_at": "2024-07-22T14:41:32Z", "updated_at": "2024-08-18T09:02:43Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2407.15673v3" }, "canonical_source_url": "https://arxiv.org/abs/2407.15673", "catalog_id": "arxiv:2407.15673", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-07-22", "identifiers": { "arxiv": "2407.15673" }, "record_updated_at": "2024-08-18" }, "genre": "preprint", "id": "arxiv:2407.15673", "issued": { "date-parts": [ [ 2024, 7, 22 ] ] }, "note": "First published: 2024-07-22; Recorded arXiv version: v3; Recorded version updated: 2024-08-18T09:02:43Z.", "title": "IDA: Breaking Barriers in No-code UI Automation Through Large Language Models and Human-Centric Design", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2506.07217v2", "archive": "arXiv", "archive_location": "2506.07217", "author": [ { "literal": "Zihan Deng" }, { "literal": "Changyu Du" }, { "literal": "Stavros Nousias" }, { "literal": "André Borrmann" } ], "citation-key": "arxiv_2506_07217", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2bf4f91de32fdf3bd9b81ba64ace02e4a7d02ff094794f30dfd560389f334cea", "submitted_at": "2025-06-08T16:45:31Z", "updated_at": "2025-06-30T08:31:07Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2506.07217v2" }, "canonical_source_url": "https://arxiv.org/abs/2506.07217", "catalog_id": "arxiv:2506.07217", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-06-08", "identifiers": { "arxiv": "2506.07217" }, "record_updated_at": "2025-06-30" }, "genre": "preprint", "id": "arxiv:2506.07217", "issued": { "date-parts": [ [ 2025, 6, 8 ] ] }, "note": "First published: 2025-06-08; Recorded arXiv version: v2; Recorded version updated: 2025-06-30T08:31:07Z.", "title": "BIMgent: Towards Autonomous Building Modeling via Computer-use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2509.13704v1", "archive": "arXiv", "archive_location": "2509.13704", "author": [ { "literal": "Liangtao Lin" }, { "literal": "Zhaomeng Zhu" }, { "literal": "Tianwei Zhang" }, { "literal": "Yonggang Wen" } ], "citation-key": "arxiv_2509_13704", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2c1a4019df77278943829e16b155771abb1c8ca30726044cf5969227e0437f5f", "submitted_at": "2025-09-17T05:14:11Z", "updated_at": "2025-09-17T05:14:11Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.13704v1" }, "canonical_source_url": "https://arxiv.org/abs/2509.13704", "catalog_id": "arxiv:2509.13704", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-17", "identifiers": { "arxiv": "2509.13704" }, "record_updated_at": "2025-09-17" }, "genre": "preprint", "id": "arxiv:2509.13704", "issued": { "date-parts": [ [ 2025, 9, 17 ] ] }, "note": "First published: 2025-09-17; Recorded arXiv version: v1; Recorded version updated: 2025-09-17T05:14:11Z.", "title": "InfraMind: A Novel Exploration-based GUI Agentic Framework for Mission-critical Industrial Management", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2509.21982v2", "archive": "arXiv", "archive_location": "2509.21982", "author": [ { "literal": "Renqi Chen" }, { "literal": "Zeyin Tao" }, { "literal": "Jianming Guo" }, { "literal": "Jingzhe Zhu" }, { "literal": "Yiheng Peng" }, { "literal": "Qingqing Sun" }, { "literal": "Tianyi Zhang" }, { "literal": "Shuai Chen" } ], "citation-key": "arxiv_2509_21982", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d23b9f33282f77b9d4965078ca993bcf21163dc1d3210aaa4e554d4fc12b37c5", "submitted_at": "2025-09-26T07:05:01Z", "updated_at": "2026-04-13T03:14:30Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2509.21982v2" }, "canonical_source_url": "https://arxiv.org/abs/2509.21982", "catalog_id": "arxiv:2509.21982", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-26", "identifiers": { "arxiv": "2509.21982" }, "record_updated_at": "2026-04-13" }, "genre": "preprint", "id": "arxiv:2509.21982", "issued": { "date-parts": [ [ 2025, 9, 26 ] ] }, "note": "First published: 2025-09-26; Recorded arXiv version: v2; Recorded version updated: 2026-04-13T03:14:30Z.", "title": "RISK: A Framework for GUI Agents in E-commerce Risk Management", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2509.26506v1", "archive": "arXiv", "archive_location": "2509.26506", "author": [ { "literal": "Yutong Dai" }, { "literal": "Krithika Ramakrishnan" }, { "literal": "Jing Gu" }, { "literal": "Matthew Fernandez" }, { "literal": "Yanqi Luo" }, { "literal": "Viraj Prabhu" }, { "literal": "Zhenyu Hu" }, { "literal": "Silvio Savarese" }, { "literal": "Caiming Xiong" }, { "literal": "Zeyuan Chen" }, { "literal": "Ran Xu" } ], "citation-key": "arxiv_2509_26506", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "0e22d26dfbda8530f32d4686f26d91ea1a8e8c5470e857f2e13803258a2f7aaf", "submitted_at": "2025-09-30T16:48:49Z", "updated_at": "2025-09-30T16:48:49Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2509.26506v1" }, "canonical_source_url": "https://arxiv.org/abs/2509.26506", "catalog_id": "arxiv:2509.26506", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-09-30", "identifiers": { "arxiv": "2509.26506" }, "record_updated_at": "2025-09-30" }, "genre": "preprint", "id": "arxiv:2509.26506", "issued": { "date-parts": [ [ 2025, 9, 30 ] ] }, "note": "First published: 2025-09-30; Recorded arXiv version: v1; Recorded version updated: 2025-09-30T16:48:49Z.", "title": "SCUBA: Salesforce Computer Use Benchmark", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2511.17131v1", "archive": "arXiv", "archive_location": "2511.17131", "author": [ { "literal": "Horia Cristescu" }, { "literal": "Charles Park" }, { "literal": "Trong Canh Nguyen" }, { "literal": "Sergiu Talmacel" }, { "literal": "Alexandru-Gabriel Ilie" }, { "literal": "Stefan Adam" } ], "citation-key": "arxiv_2511_17131", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4c746b329229d90dbe3d04a138f54c8b205b16ec6173cf681d47a319c8f24ddf", "submitted_at": "2025-11-21T10:47:22Z", "updated_at": "2025-11-21T10:47:22Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2511.17131v1" }, "canonical_source_url": "https://arxiv.org/abs/2511.17131", "catalog_id": "arxiv:2511.17131", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-11-21", "identifiers": { "arxiv": "2511.17131" }, "record_updated_at": "2025-11-21" }, "genre": "preprint", "id": "arxiv:2511.17131", "issued": { "date-parts": [ [ 2025, 11, 21 ] ] }, "note": "First published: 2025-11-21; Recorded arXiv version: v1; Recorded version updated: 2025-11-21T10:47:22Z.", "title": "UI-CUBE: Enterprise-Grade Computer Use Agent Benchmarking Beyond Task Accuracy to Operational Reliability", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2512.04105v1", "archive": "arXiv", "archive_location": "2512.04105", "author": [ { "literal": "Jinzhe Tan" }, { "literal": "Karim Benyekhlef" } ], "citation-key": "arxiv_2512_04105", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d362a839fd1ee917ebdde6fcd794640523e930cd711769154532200903fe7de5", "submitted_at": "2025-11-28T07:26:29Z", "updated_at": "2025-11-28T07:26:29Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2512.04105v1" }, "canonical_source_url": "https://arxiv.org/abs/2512.04105", "catalog_id": "arxiv:2512.04105", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-11-28", "identifiers": { "arxiv": "2512.04105" }, "record_updated_at": "2025-11-28" }, "genre": "preprint", "id": "arxiv:2512.04105", "issued": { "date-parts": [ [ 2025, 11, 28 ] ] }, "note": "First published: 2025-11-28; Recorded arXiv version: v1; Recorded version updated: 2025-11-28T07:26:29Z.", "title": "LegalWebAgent: Empowering Access to Justice via LLM-Based Web Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2512.11611v1", "archive": "arXiv", "archive_location": "2512.11611", "author": [ { "literal": "Chunyi Li" }, { "literal": "Longfei Li" }, { "literal": "Zicheng Zhang" }, { "literal": "Xiaohong Liu" }, { "literal": "Min Tang" }, { "literal": "Weisi Lin" }, { "literal": "Guangtao Zhai" } ], "citation-key": "arxiv_2512_11611", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "484a51656db4466d5e8630d64fa78d3cf10043568488f5a2e9bae679fa800cbe", "submitted_at": "2025-12-12T14:49:32Z", "updated_at": "2025-12-12T14:49:32Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2512.11611v1" }, "canonical_source_url": "https://arxiv.org/abs/2512.11611", "catalog_id": "arxiv:2512.11611", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-12", "identifiers": { "arxiv": "2512.11611" }, "record_updated_at": "2025-12-12" }, "genre": "preprint", "id": "arxiv:2512.11611", "issued": { "date-parts": [ [ 2025, 12, 12 ] ] }, "note": "First published: 2025-12-12; Recorded arXiv version: v1; Recorded version updated: 2025-12-12T14:49:32Z.", "title": "Using GUI Agent for Electronic Design Automation", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2601.02399v1", "archive": "arXiv", "archive_location": "2601.02399", "author": [ { "literal": "Jiaxin Ai" }, { "literal": "Yukang Feng" }, { "literal": "Fanrui Zhang" }, { "literal": "Jianwen Sun" }, { "literal": "Zizhen Li" }, { "literal": "Chuanhao Li" }, { "literal": "Yifan Chang" }, { "literal": "Wenxiao Wu" }, { "literal": "Ruoxi Wang" }, { "literal": "Mingliang Zhai" }, { "literal": "Kaipeng Zhang" } ], "citation-key": "arxiv_2601_02399", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "afab3dcd2444bf8333f2a2fea887819f6fca55c41209d8c449f6211d1c62b819", "submitted_at": "2025-12-30T01:49:46Z", "updated_at": "2025-12-30T01:49:46Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2601.02399v1" }, "canonical_source_url": "https://arxiv.org/abs/2601.02399", "catalog_id": "arxiv:2601.02399", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-30", "identifiers": { "arxiv": "2601.02399" }, "record_updated_at": "2025-12-30" }, "genre": "preprint", "id": "arxiv:2601.02399", "issued": { "date-parts": [ [ 2025, 12, 30 ] ] }, "note": "First published: 2025-12-30; Recorded arXiv version: v1; Recorded version updated: 2025-12-30T01:49:46Z.", "title": "ProSoftArena: Benchmarking Hierarchical Capabilities of Multimodal Agents in Professional Software Environments", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2601.17722v1", "archive": "arXiv", "archive_location": "2601.17722", "author": [ { "literal": "Ying Mo" }, { "literal": "Yu Bai" }, { "literal": "Dapeng Sun" }, { "literal": "Yuqian Shi" }, { "literal": "Yukai Miao" }, { "literal": "Li Chen" }, { "literal": "Dan Li" } ], "citation-key": "arxiv_2601_17722", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "fa7c8ce1b0e584c5279691ff06cd522d7c8ea1f4801d7074324c6845ce482efb", "submitted_at": "2026-01-25T06:58:15Z", "updated_at": "2026-01-25T06:58:15Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2601.17722v1" }, "canonical_source_url": "https://arxiv.org/abs/2601.17722", "catalog_id": "arxiv:2601.17722", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-25", "identifiers": { "arxiv": "2601.17722" }, "record_updated_at": "2026-01-25" }, "genre": "preprint", "id": "arxiv:2601.17722", "issued": { "date-parts": [ [ 2026, 1, 25 ] ] }, "note": "First published: 2026-01-25; Recorded arXiv version: v1; Recorded version updated: 2026-01-25T06:58:15Z.", "title": "EntWorld: A Holistic Environment and Benchmark for Verifiable Enterprise GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.09937v1", "archive": "arXiv", "archive_location": "2604.09937", "author": [ { "literal": "Suhana Bedi" }, { "literal": "Ryan Welch" }, { "literal": "Ethan Steinberg" }, { "literal": "Michael Wornow" }, { "literal": "Taeil Matthew Kim" }, { "literal": "Haroun Ahmed" }, { "literal": "Peter Sterling" }, { "literal": "Bravim Purohit" }, { "literal": "Qurat Akram" }, { "literal": "Angelic Acosta" }, { "literal": "Esther Nubla" }, { "literal": "Pritika Sharma" }, { "literal": "Michael A. Pfeffer" }, { "literal": "Sanmi Koyejo" }, { "literal": "Nigam H. Shah" } ], "citation-key": "arxiv_2604_09937", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "55cedd4ad9760618fe9b3354e384f69b69b23b65f75837a3898484c9c6e55586", "submitted_at": "2026-04-10T22:33:39Z", "updated_at": "2026-04-10T22:33:39Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.09937v1" }, "canonical_source_url": "https://arxiv.org/abs/2604.09937", "catalog_id": "arxiv:2604.09937", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-10", "identifiers": { "arxiv": "2604.09937" }, "record_updated_at": "2026-04-10" }, "genre": "preprint", "id": "arxiv:2604.09937", "issued": { "date-parts": [ [ 2026, 4, 10 ] ] }, "note": "First published: 2026-04-10; Recorded arXiv version: v1; Recorded version updated: 2026-04-10T22:33:39Z.", "title": "HealthAdminBench: Evaluating Computer-Use Agents on Healthcare Administration Tasks", "type": "article", "version": "1" } ]