[ { "URL": "https://arxiv.org/abs/2407.10956v1", "archive": "arXiv", "archive_location": "2407.10956", "author": [ { "literal": "Ruisheng Cao" }, { "literal": "Fangyu Lei" }, { "literal": "Haoyuan Wu" }, { "literal": "Jixuan Chen" }, { "literal": "Yeqiao Fu" }, { "literal": "Hongcheng Gao" }, { "literal": "Xinzhuang Xiong" }, { "literal": "Hanchong Zhang" }, { "literal": "Yuchen Mao" }, { "literal": "Wenjing Hu" }, { "literal": "Tianbao Xie" }, { "literal": "Hongshen Xu" }, { "literal": "Danyang Zhang" }, { "literal": "Sida Wang" }, { "literal": "Ruoxi Sun" }, { "literal": "Pengcheng Yin" }, { "literal": "Caiming Xiong" }, { "literal": "Ansong Ni" }, { "literal": "Qian Liu" }, { "literal": "Victor Zhong" }, { "literal": "Lu Chen" }, { "literal": "Kai Yu" }, { "literal": "Tao Yu" } ], "citation-key": "arxiv_2407_10956", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7922a723142ac62018064fe5fc9357fb77c08e316ac4d6d6ba728f1b337df690", "submitted_at": "2024-07-15T17:54:37Z", "updated_at": "2024-07-15T17:54:37Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2407.10956v1" }, "canonical_source_url": "https://arxiv.org/abs/2407.10956", "catalog_id": "arxiv:2407.10956", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "citation_edition": "record", "first_published_at": "2024-07-15", "identifiers": { "arxiv": "2407.10956" }, "publication": { "authors": [ "Ruisheng Cao", "Fangyu Lei", "Haoyuan Wu", "Jixuan Chen", "Yeqiao Fu", "Hongcheng Gao", "Xinzhuang Xiong", "Hanchong Zhang", "Yuchen Mao", "Wenjing Hu", "Tianbao Xie", "Hongshen Xu", "Danyang Zhang", "Sida Wang", "Ruoxi Sun", "Pengcheng Yin", "Caiming Xiong", "Ansong Ni", "Qian Liu", "Victor Zhong", "Lu Chen", "Kai Yu", "Tao Yu" ], "date_basis": "Explicit publisher citation_publication_date: 2024-12-16. Preserve supplied precision; do not substitute conference event dates.", "date_parts": [ 2024, 12, 16 ], "doi": "10.52202/079017-3421", "event_dates": null, "evidence_urls": [ "https://proceedings.neurips.cc/paper_files/paper/2024/hash/c2f71567cd53464161cab3336e8fc865-Abstract-Datasets_and_Benchmarks_Track.html" ], "identity_basis": "Same work: normalized title, ordered author correspondence and the specific contribution in the complete publisher abstract were reviewed against the retained arXiv identity. The normalized publisher abstract matches the retained arXiv abstract SHA-256.", "issue": null, "notes": "Publisher proceedings edition; retained separately from the arXiv snapshot.", "pages": "107703-107744", "pdf_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/c2f71567cd53464161cab3336e8fc865-Paper-Datasets_and_Benchmarks_Track.pdf", "publisher": null, "series": null, "title": "Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?", "type": "conference-paper", "url": "https://proceedings.neurips.cc/paper_files/paper/2024/hash/c2f71567cd53464161cab3336e8fc865-Abstract-Datasets_and_Benchmarks_Track.html", "venue": "Advances in Neural Information Processing Systems", "volume": "37" }, "record_updated_at": "2024-07-15" }, "genre": "preprint", "id": "arxiv:2407.10956", "issued": { "date-parts": [ [ 2024, 7, 15 ] ] }, "note": "First published: 2024-07-15; Recorded arXiv version: v1; Recorded version updated: 2024-07-15T17:54:37Z.", "title": "Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2505.19897v3", "archive": "arXiv", "archive_location": "2505.19897", "author": [ { "literal": "Qiushi Sun" }, { "literal": "Zhoumianze Liu" }, { "literal": "Chang Ma" }, { "literal": "Zichen Ding" }, { "literal": "Fangzhi Xu" }, { "literal": "Zhangyue Yin" }, { "literal": "Haiteng Zhao" }, { "literal": "Zhenyu Wu" }, { "literal": "Kanzhi Cheng" }, { "literal": "Zhaoyang Liu" }, { "literal": "Jianing Wang" }, { "literal": "Qintong Li" }, { "literal": "Xiangru Tang" }, { "literal": "Tianbao Xie" }, { "literal": "Xiachong Feng" }, { "literal": "Xiang Li" }, { "literal": "Ben Kao" }, { "literal": "Wenhai Wang" }, { "literal": "Biqing Qi" }, { "literal": "Lingpeng Kong" }, { "literal": "Zhiyong Wu" } ], "citation-key": "arxiv_2505_19897", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4743f6bfd0ca48717184cf55545e33a229dd5ab2d454385d33ea2f1b25c15b0c", "submitted_at": "2025-05-26T12:27:27Z", "updated_at": "2026-04-20T16:29:04Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2505.19897v3" }, "canonical_source_url": "https://arxiv.org/abs/2505.19897", "catalog_id": "arxiv:2505.19897", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-26", "identifiers": { "arxiv": "2505.19897" }, "record_updated_at": "2026-04-20" }, "genre": "preprint", "id": "arxiv:2505.19897", "issued": { "date-parts": [ [ 2025, 5, 26 ] ] }, "note": "First published: 2025-05-26; Recorded arXiv version: v3; Recorded version updated: 2026-04-20T16:29:04Z.", "title": "ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows", "type": "article", "version": "3" }, { "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/2508.20096v1", "archive": "arXiv", "archive_location": "2508.20096", "author": [ { "literal": "Zeyi Sun" }, { "literal": "Yuhang Cao" }, { "literal": "Jianze Liang" }, { "literal": "Qiushi Sun" }, { "literal": "Ziyu Liu" }, { "literal": "Zhixiong Zhang" }, { "literal": "Yuhang Zang" }, { "literal": "Xiaoyi Dong" }, { "literal": "Kai Chen" }, { "literal": "Dahua Lin" }, { "literal": "Jiaqi Wang" } ], "citation-key": "arxiv_2508_20096", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ac401f8d5c56050e72839f3bffba4f2c78bbdf34a00cab05fe504f03efd96a19", "submitted_at": "2025-08-27T17:59:50Z", "updated_at": "2025-08-27T17:59:50Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2508.20096v1" }, "canonical_source_url": "https://arxiv.org/abs/2508.20096", "catalog_id": "arxiv:2508.20096", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-08-27", "identifiers": { "arxiv": "2508.20096" }, "record_updated_at": "2025-08-27" }, "genre": "preprint", "id": "arxiv:2508.20096", "issued": { "date-parts": [ [ 2025, 8, 27 ] ] }, "note": "First published: 2025-08-27; Recorded arXiv version: v1; Recorded version updated: 2025-08-27T17:59:50Z.", "title": "CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning", "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/2604.27996v3", "archive": "arXiv", "archive_location": "2604.27996", "author": [ { "literal": "Jackson Vonderhorst" }, { "literal": "Kuangshi Ai" }, { "literal": "Haichao Miao" }, { "literal": "Shusen Liu" }, { "literal": "Chaoli Wang" } ], "citation-key": "arxiv_2604_27996", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8e7b07a811df7e74a28f91a5b6c59c69b7ba066bd6c64452a299e678a3187733", "submitted_at": "2026-04-30T15:22:28Z", "updated_at": "2026-06-26T20:31:32Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2604.27996v3" }, "canonical_source_url": "https://arxiv.org/abs/2604.27996", "catalog_id": "arxiv:2604.27996", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-04-30", "identifiers": { "arxiv": "2604.27996" }, "record_updated_at": "2026-06-26" }, "genre": "preprint", "id": "arxiv:2604.27996", "issued": { "date-parts": [ [ 2026, 4, 30 ] ] }, "note": "First published: 2026-04-30; Recorded arXiv version: v3; Recorded version updated: 2026-06-26T20:31:32Z.", "title": "Exploring LLM Agent Designs and Interaction Modalities for Scientific Visualization", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2606.03203v1", "archive": "arXiv", "archive_location": "2606.03203", "author": [ { "literal": "Jia Yu" }, { "literal": "Zilong Wang" }, { "literal": "Xinyang Jiang" }, { "literal": "Dongsheng Li" }, { "literal": "Shuo Wang" } ], "citation-key": "arxiv_2606_03203", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "b23c12cafdd2d4a3ef63027c914ed3894c61c555edd89468c56ae40c3ec6cea9", "submitted_at": "2026-06-02T06:02:35Z", "updated_at": "2026-06-02T06:02:35Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2606.03203v1" }, "canonical_source_url": "https://arxiv.org/abs/2606.03203", "catalog_id": "arxiv:2606.03203", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-06-02", "identifiers": { "arxiv": "2606.03203" }, "record_updated_at": "2026-06-02" }, "genre": "preprint", "id": "arxiv:2606.03203", "issued": { "date-parts": [ [ 2026, 6, 2 ] ] }, "note": "First published: 2026-06-02; Recorded arXiv version: v1; Recorded version updated: 2026-06-02T06:02:35Z.", "title": "MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2606.13239v2", "archive": "arXiv", "archive_location": "2606.13239", "author": [ { "literal": "Jiaxin Ai" }, { "literal": "Tao Hu" }, { "literal": "Xuemeng Yang" }, { "literal": "Shu Zou" }, { "literal": "Hairong Zhang" }, { "literal": "Daocheng Fu" }, { "literal": "Yu Yang" }, { "literal": "Hongbin Zhou" }, { "literal": "Nianchen Deng" }, { "literal": "Pinlong Cai" }, { "literal": "Zhongyuan Wang" }, { "literal": "Botian Shi" }, { "literal": "Kaipeng Zhang" }, { "literal": "Licheng Wen" } ], "citation-key": "arxiv_2606_13239", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "edf7e63803efba89551aa297bff1da9b0babf8ec898a2971fa6c8a20cc58dea8", "submitted_at": "2026-06-11T11:53:32Z", "updated_at": "2026-06-30T03:31:20Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2606.13239v2" }, "canonical_source_url": "https://arxiv.org/abs/2606.13239", "catalog_id": "arxiv:2606.13239", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-06-11", "identifiers": { "arxiv": "2606.13239" }, "record_updated_at": "2026-06-30" }, "genre": "preprint", "id": "arxiv:2606.13239", "issued": { "date-parts": [ [ 2026, 6, 11 ] ] }, "note": "First published: 2026-06-11; Recorded arXiv version: v2; Recorded version updated: 2026-06-30T03:31:20Z.", "title": "ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm", "type": "article", "version": "2" }, { "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/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/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/2609.37053v1", "archive": "arXiv", "archive_location": "2609.37053", "author": [ { "literal": "Mei Wu" }, { "literal": "Rui Xie" }, { "literal": "Runyu Zhang" }, { "literal": "Yuqiang Li" }, { "literal": "Tianfan Fu" }, { "literal": "Bo Chen" }, { "literal": "Kai Yu" }, { "literal": "Xin Chen" }, { "literal": "Lu Chen" } ], "citation-key": "arxiv_2609_37053", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e032f67257a52dbc59310d921d802e4dc85af3af110d22bb6d005d202bbaa6b2", "submitted_at": "2026-09-29T08:58:51Z", "updated_at": "2026-09-29T08:58:51Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.37053v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.37053", "catalog_id": "arxiv:2609.37053", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-29", "identifiers": { "arxiv": "2609.37053" }, "record_updated_at": "2026-09-29" }, "genre": "preprint", "id": "arxiv:2609.37053", "issued": { "date-parts": [ [ 2026, 9, 29 ] ] }, "note": "First published: 2026-09-29; Recorded arXiv version: v1; Recorded version updated: 2026-09-29T08:58:51Z.", "title": "MatToolBench: Benchmarking Multimodal Agents in Real-World Materials Science Workflows", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.37686v2", "archive": "arXiv", "archive_location": "2609.37686", "author": [ { "literal": "Hongcheng Gao" }, { "literal": "Hailong Qu" }, { "literal": "Yu Lei" }, { "literal": "Henghui Sun" }, { "literal": "Haoyang Li" }, { "literal": "Yipeng Wei" }, { "literal": "Naihao Xue" }, { "literal": "Xiaohan Yu" }, { "literal": "Zhuo Tao" }, { "literal": "Yihe Zang" }, { "literal": "Yajiao Wang" }, { "literal": "Jingyi Tang" }, { "literal": "Yi Li" }, { "literal": "Jingjing Zhou" }, { "literal": "Jie Luo" }, { "literal": "Bohan Zeng" }, { "literal": "Chengyu Shen" }, { "literal": "Hao Jiang" }, { "literal": "Chong Chen" }, { "literal": "Bowen Qu" }, { "literal": "Olive Huang" }, { "literal": "Zeqiang Wang" } ], "citation-key": "arxiv_2609_37686", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "aab7f586cb58a1f2d20267fd810ba34d6d4d166e3da715d2b3ff0b77e464473e", "submitted_at": "2026-09-29T14:32:35Z", "updated_at": "2026-10-09T08:15:21Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2609.37686v2" }, "canonical_source_url": "https://arxiv.org/abs/2609.37686", "catalog_id": "arxiv:2609.37686", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-29", "identifiers": { "arxiv": "2609.37686" }, "record_updated_at": "2026-10-09" }, "genre": "preprint", "id": "arxiv:2609.37686", "issued": { "date-parts": [ [ 2026, 9, 29 ] ] }, "note": "First published: 2026-09-29; Recorded arXiv version: v2; Recorded version updated: 2026-10-09T08:15:21Z.", "title": "EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2609.39903v1", "archive": "arXiv", "archive_location": "2609.39903", "author": [ { "literal": "Dingyuan Dai" }, { "literal": "Heli Qi" }, { "literal": "Lei Liu" }, { "literal": "Yinxi Li" }, { "literal": "Baiding Chen" }, { "literal": "Zijun Dou" }, { "literal": "Qingcheng Zeng" }, { "literal": "Qi Kang" }, { "literal": "Oliver Sun" }, { "literal": "Eric Wang" }, { "literal": "Bo Zhou" }, { "literal": "Haixin Wang" }, { "literal": "Yufan Du" }, { "literal": "Shi Bo" }, { "literal": "Ruihan Lin" }, { "literal": "Mengqi Yuan" }, { "literal": "Dunjie Lu" }, { "literal": "Steven Dillmann" }, { "literal": "Yiming Shi" }, { "literal": "Tina Su" }, { "literal": "Amy Xin" }, { "literal": "Minghao Liu" }, { "literal": "Xi Wang" }, { "literal": "Xu Huang" }, { "literal": "Ge Zhang" }, { "literal": "Pengyu Nie" }, { "literal": "Zhen Yang" }, { "literal": "Jie Tang" }, { "literal": "Juanzi Li" }, { "literal": "Weihao Xuan" }, { "literal": "Tianyu Liu" } ], "citation-key": "arxiv_2609_39903", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "690cd75934bae65311240cd4e6db7b8fd607056bd60799bf70cddd03efda9261", "submitted_at": "2026-09-30T15:03:05Z", "updated_at": "2026-09-30T15:03:05Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.39903v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.39903", "catalog_id": "arxiv:2609.39903", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-30", "identifiers": { "arxiv": "2609.39903" }, "record_updated_at": "2026-09-30" }, "genre": "preprint", "id": "arxiv:2609.39903", "issued": { "date-parts": [ [ 2026, 9, 30 ] ] }, "note": "First published: 2026-09-30; Recorded arXiv version: v1; Recorded version updated: 2026-09-30T15:03:05Z.", "title": "OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.04800v1", "archive": "arXiv", "archive_location": "2610.04800", "author": [ { "literal": "Ziyang Long" }, { "literal": "Xinqi Li" }, { "literal": "Lujing Xing" }, { "literal": "Hsin-Jung Yang" } ], "citation-key": "arxiv_2610_04800", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "baacd8b4fad7b146bb9152a54d60a617fdbed5d0142c0c0768dacea2e7f18e60", "submitted_at": "2026-10-03T22:56:09Z", "updated_at": "2026-10-03T22:56:09Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.04800v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.04800", "catalog_id": "arxiv:2610.04800", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-03", "identifiers": { "arxiv": "2610.04800" }, "record_updated_at": "2026-10-03" }, "genre": "preprint", "id": "arxiv:2610.04800", "issued": { "date-parts": [ [ 2026, 10, 3 ] ] }, "note": "First published: 2026-10-03; Recorded arXiv version: v1; Recorded version updated: 2026-10-03T22:56:09Z.", "title": "MedImageOSWorld: Benchmarking GUI Agents for Medical Image Consoles", "type": "article", "version": "1" } ]