[ { "URL": "https://arxiv.org/abs/2406.07822v2", "archive": "arXiv", "archive_location": "2406.07822", "author": [ { "literal": "Andrea Burns" }, { "literal": "Kate Saenko" }, { "literal": "Bryan A. Plummer" } ], "citation-key": "arxiv_2406_07822", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "47d0ca0467a104f9b8be037ec73131f12b66a22b0a89fe975bec7680073c8f39", "submitted_at": "2024-06-12T02:43:19Z", "updated_at": "2024-08-08T02:36:04Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2406.07822v2" }, "canonical_source_url": "https://arxiv.org/abs/2406.07822", "catalog_id": "arxiv:2406.07822", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-06-12", "identifiers": { "arxiv": "2406.07822" }, "record_updated_at": "2024-08-08" }, "genre": "preprint", "id": "arxiv:2406.07822", "issued": { "date-parts": [ [ 2024, 6, 12 ] ] }, "note": "First published: 2024-06-12; Recorded arXiv version: v2; Recorded version updated: 2024-08-08T02:36:04Z.", "title": "Tell Me What's Next: Textual Foresight for Generic UI Representations", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2410.13232v2", "archive": "arXiv", "archive_location": "2410.13232", "author": [ { "literal": "Hyungjoo Chae" }, { "literal": "Namyoung Kim" }, { "literal": "Kai Tzu-iunn Ong" }, { "literal": "Minju Gwak" }, { "literal": "Gwanwoo Song" }, { "literal": "Jihoon Kim" }, { "literal": "Sunghwan Kim" }, { "literal": "Dongha Lee" }, { "literal": "Jinyoung Yeo" } ], "citation-key": "arxiv_2410_13232", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "cae86bff4412bbfa7b969ecd60fe7b695f4b7c5ea1be6a67e97919df762d1108", "submitted_at": "2024-10-17T05:37:00Z", "updated_at": "2025-03-29T08:59:09Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2410.13232v2" }, "canonical_source_url": "https://arxiv.org/abs/2410.13232", "catalog_id": "arxiv:2410.13232", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-10-17", "identifiers": { "arxiv": "2410.13232" }, "record_updated_at": "2025-03-29" }, "genre": "preprint", "id": "arxiv:2410.13232", "issued": { "date-parts": [ [ 2024, 10, 17 ] ] }, "note": "First published: 2024-10-17; Recorded arXiv version: v2; Recorded version updated: 2025-03-29T08:59:09Z.", "title": "Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2411.06559v2", "archive": "arXiv", "archive_location": "2411.06559", "author": [ { "literal": "Yu Gu" }, { "literal": "Kai Zhang" }, { "literal": "Yuting Ning" }, { "literal": "Boyuan Zheng" }, { "literal": "Boyu Gou" }, { "literal": "Tianci Xue" }, { "literal": "Cheng Chang" }, { "literal": "Sanjari Srivastava" }, { "literal": "Yanan Xie" }, { "literal": "Peng Qi" }, { "literal": "Huan Sun" }, { "literal": "Yu Su" } ], "citation-key": "arxiv_2411_06559", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9ecaca6448aae5c8849d008d820d700bfa438ed0248f85be585b0b831408b9b6", "submitted_at": "2024-11-10T18:50:51Z", "updated_at": "2025-04-01T05:04:47Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2411.06559v2" }, "canonical_source_url": "https://arxiv.org/abs/2411.06559", "catalog_id": "arxiv:2411.06559", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2024-11-10", "identifiers": { "arxiv": "2411.06559" }, "record_updated_at": "2025-04-01" }, "genre": "preprint", "id": "arxiv:2411.06559", "issued": { "date-parts": [ [ 2024, 11, 10 ] ] }, "note": "First published: 2024-11-10; Recorded arXiv version: v2; Recorded version updated: 2025-04-01T05:04:47Z.", "title": "Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2502.18906v1", "archive": "arXiv", "archive_location": "2502.18906", "author": [ { "literal": "Jiani Zheng" }, { "literal": "Lu Wang" }, { "literal": "Fangkai Yang" }, { "literal": "Chaoyun Zhang" }, { "literal": "Lingrui Mei" }, { "literal": "Wenjie Yin" }, { "literal": "Qingwei Lin" }, { "literal": "Dongmei Zhang" }, { "literal": "Saravan Rajmohan" }, { "literal": "Qi Zhang" } ], "citation-key": "arxiv_2502_18906", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6d69b006a298a591aacfe7f29df63f508113c0ec824ede82a0bb5bbb9cb66266", "submitted_at": "2025-02-26T07:52:02Z", "updated_at": "2025-02-26T07:52:02Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2502.18906v1" }, "canonical_source_url": "https://arxiv.org/abs/2502.18906", "catalog_id": "arxiv:2502.18906", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-02-26", "identifiers": { "arxiv": "2502.18906" }, "record_updated_at": "2025-02-26" }, "genre": "preprint", "id": "arxiv:2502.18906", "issued": { "date-parts": [ [ 2025, 2, 26 ] ] }, "note": "First published: 2025-02-26; Recorded arXiv version: v1; Recorded version updated: 2025-02-26T07:52:02Z.", "title": "VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2504.13936v2", "archive": "arXiv", "archive_location": "2504.13936", "author": [ { "literal": "Dezhao Luo" }, { "literal": "Bohan Tang" }, { "literal": "Kang Li" }, { "literal": "Georgios Papoudakis" }, { "literal": "Jifei Song" }, { "literal": "Shaogang Gong" }, { "literal": "Jianye Hao" }, { "literal": "Jun Wang" }, { "literal": "Kun Shao" } ], "citation-key": "arxiv_2504_13936", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "15e00237ef710c37c0c9f7768d699f57e9d5dcc190e8de7e20e9ec3b21b82750", "submitted_at": "2025-04-15T14:03:10Z", "updated_at": "2025-05-20T14:11:37Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2504.13936v2" }, "canonical_source_url": "https://arxiv.org/abs/2504.13936", "catalog_id": "arxiv:2504.13936", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-04-15", "identifiers": { "arxiv": "2504.13936" }, "record_updated_at": "2025-05-20" }, "genre": "preprint", "id": "arxiv:2504.13936", "issued": { "date-parts": [ [ 2025, 4, 15 ] ] }, "note": "First published: 2025-04-15; Recorded arXiv version: v2; Recorded version updated: 2025-05-20T14:11:37Z.", "title": "ViMo: A Generative Visual GUI World Model for App Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2504.21024v2", "archive": "arXiv", "archive_location": "2504.21024", "author": [ { "literal": "Tianqing Fang" }, { "literal": "Hongming Zhang" }, { "literal": "Zhisong Zhang" }, { "literal": "Kaixin Ma" }, { "literal": "Wenhao Yu" }, { "literal": "Haitao Mi" }, { "literal": "Dong Yu" } ], "citation-key": "arxiv_2504_21024", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "86ca58c92ffc2cbbcb0297d8c7618dfab966e36a07b141c068998b0f2934d11e", "submitted_at": "2025-04-23T02:54:31Z", "updated_at": "2025-08-21T05:55:43Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2504.21024v2" }, "canonical_source_url": "https://arxiv.org/abs/2504.21024", "catalog_id": "arxiv:2504.21024", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-04-23", "identifiers": { "arxiv": "2504.21024" }, "record_updated_at": "2025-08-21" }, "genre": "preprint", "id": "arxiv:2504.21024", "issued": { "date-parts": [ [ 2025, 4, 23 ] ] }, "note": "First published: 2025-04-23; Recorded arXiv version: v2; Recorded version updated: 2025-08-21T05:55:43Z.", "title": "WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2505.16422v3", "archive": "arXiv", "archive_location": "2505.16422", "author": [ { "literal": "Xiaoran Yin" }, { "literal": "Xu Luo" }, { "literal": "Hao Wu" }, { "literal": "Lianli Gao" }, { "literal": "Jingkuan Song" } ], "citation-key": "arxiv_2505_16422", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "93c67222fb0f581e9f9cb3ff59c8d28faec9dc037180060ad5ac962b4469144c", "submitted_at": "2025-05-22T09:08:47Z", "updated_at": "2025-09-05T02:24:00Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2505.16422v3" }, "canonical_source_url": "https://arxiv.org/abs/2505.16422", "catalog_id": "arxiv:2505.16422", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-22", "identifiers": { "arxiv": "2505.16422" }, "record_updated_at": "2025-09-05" }, "genre": "preprint", "id": "arxiv:2505.16422", "issued": { "date-parts": [ [ 2025, 5, 22 ] ] }, "note": "First published: 2025-05-22; Recorded arXiv version: v3; Recorded version updated: 2025-09-05T02:24:00Z.", "title": "Unlocking Smarter Device Control: Foresighted Planning with a World Model-Driven Code Execution Approach", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2505.19095v1", "archive": "arXiv", "archive_location": "2505.19095", "author": [ { "literal": "Runliang Niu" }, { "literal": "Jinglong Ji" }, { "literal": "Yi Chang" }, { "literal": "Qi Wang" } ], "citation-key": "arxiv_2505_19095", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bb782466eccc7a271c89a4161c7b142f93f8f0d585cad39a1ccad048cf514426", "submitted_at": "2025-05-25T11:13:03Z", "updated_at": "2025-05-25T11:13:03Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2505.19095v1" }, "canonical_source_url": "https://arxiv.org/abs/2505.19095", "catalog_id": "arxiv:2505.19095", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-05-25", "identifiers": { "arxiv": "2505.19095" }, "record_updated_at": "2025-05-25" }, "genre": "preprint", "id": "arxiv:2505.19095", "issued": { "date-parts": [ [ 2025, 5, 25 ] ] }, "note": "First published: 2025-05-25; Recorded arXiv version: v1; Recorded version updated: 2025-05-25T11:13:03Z.", "title": "ScreenExplorer: Training a Vision-Language Model for Diverse Exploration in Open GUI World", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2508.04700v2", "archive": "arXiv", "archive_location": "2508.04700", "author": [ { "literal": "Zeyi Sun" }, { "literal": "Ziyu Liu" }, { "literal": "Yuhang Zang" }, { "literal": "Yuhang Cao" }, { "literal": "Xiaoyi Dong" }, { "literal": "Tong Wu" }, { "literal": "Dahua Lin" }, { "literal": "Jiaqi Wang" } ], "citation-key": "arxiv_2508_04700", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "268c38e6f11f11771a1251fc522112ff052557b5753dff6cadf2ba49c0ec04b2", "submitted_at": "2025-08-06T17:58:46Z", "updated_at": "2025-08-12T15:11:53Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2508.04700v2" }, "canonical_source_url": "https://arxiv.org/abs/2508.04700", "catalog_id": "arxiv:2508.04700", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-08-06", "identifiers": { "arxiv": "2508.04700" }, "record_updated_at": "2025-08-12" }, "genre": "preprint", "id": "arxiv:2508.04700", "issued": { "date-parts": [ [ 2025, 8, 6 ] ] }, "note": "First published: 2025-08-06; Recorded arXiv version: v2; Recorded version updated: 2025-08-12T15:11:53Z.", "title": "SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2510.11892v2", "archive": "arXiv", "archive_location": "2510.11892", "author": [ { "literal": "Kai Mei" }, { "literal": "Jiang Guo" }, { "literal": "Shuaichen Chang" }, { "literal": "Mingwen Dong" }, { "literal": "Dongkyu Lee" }, { "literal": "Xing Niu" }, { "literal": "Jiarong Jiang" } ], "citation-key": "arxiv_2510_11892", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7c37dae372655e8ef556163744e47ed42db3533175ca7d1db7560033774ed2a0", "submitted_at": "2025-10-13T19:52:04Z", "updated_at": "2026-03-09T15:25:16Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2510.11892v2" }, "canonical_source_url": "https://arxiv.org/abs/2510.11892", "catalog_id": "arxiv:2510.11892", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-10-13", "identifiers": { "arxiv": "2510.11892" }, "record_updated_at": "2026-03-09" }, "genre": "preprint", "id": "arxiv:2510.11892", "issued": { "date-parts": [ [ 2025, 10, 13 ] ] }, "note": "First published: 2025-10-13; Recorded arXiv version: v2; Recorded version updated: 2026-03-09T15:25:16Z.", "title": "R-WoM: Retrieval-augmented World Model For Computer-use Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2512.14014v2", "archive": "arXiv", "archive_location": "2512.14014", "author": [ { "literal": "Shufan Li" }, { "literal": "Konstantinos Kallidromitis" }, { "literal": "Akash Gokul" }, { "literal": "Yusuke Kato" }, { "literal": "Kazuki Kozuka" }, { "literal": "Aditya Grover" } ], "citation-key": "arxiv_2512_14014", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "e6228822cf64c6aeb1836bee52a6515123bd0d44d77cceb23e785bb4ff9aef47", "submitted_at": "2025-12-16T02:16:42Z", "updated_at": "2026-10-07T23:06:49Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2512.14014v2" }, "canonical_source_url": "https://arxiv.org/abs/2512.14014", "catalog_id": "arxiv:2512.14014", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2025-12-16", "identifiers": { "arxiv": "2512.14014" }, "record_updated_at": "2026-10-07" }, "genre": "preprint", "id": "arxiv:2512.14014", "issued": { "date-parts": [ [ 2025, 12, 16 ] ] }, "note": "First published: 2025-12-16; Recorded arXiv version: v2; Recorded version updated: 2026-10-07T23:06:49Z.", "title": "MobileWorldBench: Towards Semantic World Modeling For Mobile Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2601.04035v2", "archive": "arXiv", "archive_location": "2601.04035", "author": [ { "literal": "Yilin Cao" }, { "literal": "Yufeng Zhong" }, { "literal": "Zhixiong Zeng" }, { "literal": "Siran Dai" }, { "literal": "Liming Zheng" }, { "literal": "Jing Huang" }, { "literal": "Haibo Qiu" }, { "literal": "Peng Shi" }, { "literal": "Wenji Mao" } ], "citation-key": "arxiv_2601_04035", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "c40e3db3f538f089c19d7c8233ea01174d0591c3211a7acc412ee4df28e902a8", "submitted_at": "2026-01-07T15:51:44Z", "updated_at": "2026-08-31T13:27:52Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2601.04035v2" }, "canonical_source_url": "https://arxiv.org/abs/2601.04035", "catalog_id": "arxiv:2601.04035", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-07", "identifiers": { "arxiv": "2601.04035" }, "record_updated_at": "2026-08-31" }, "genre": "preprint", "id": "arxiv:2601.04035", "issued": { "date-parts": [ [ 2026, 1, 7 ] ] }, "note": "First published: 2026-01-07; Recorded arXiv version: v2; Recorded version updated: 2026-08-31T13:27:52Z.", "title": "MobileDreamer: Generative Sketch World Model for GUI Agent", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2601.22149v2", "archive": "arXiv", "archive_location": "2601.22149", "author": [ { "literal": "Hang Ding" }, { "literal": "Peidong Liu" }, { "literal": "Junqiao Wang" }, { "literal": "Ziwei Ji" }, { "literal": "Meng Cao" }, { "literal": "Rongzhao Zhang" }, { "literal": "Lynn Ai" }, { "literal": "Eric Yang" }, { "literal": "Tianyu Shi" }, { "literal": "Lei Yu" } ], "citation-key": "arxiv_2601_22149", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "aedb5ed90c91d72f62f5ab60be5374b6f431f887425bc760883ce3fb85a46d43", "submitted_at": "2026-01-29T18:59:07Z", "updated_at": "2026-04-17T18:27:53Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2601.22149v2" }, "canonical_source_url": "https://arxiv.org/abs/2601.22149", "catalog_id": "arxiv:2601.22149", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-01-29", "identifiers": { "arxiv": "2601.22149" }, "record_updated_at": "2026-04-17" }, "genre": "preprint", "id": "arxiv:2601.22149", "issued": { "date-parts": [ [ 2026, 1, 29 ] ] }, "note": "First published: 2026-01-29; Recorded arXiv version: v2; Recorded version updated: 2026-04-17T18:27:53Z.", "title": "DynaWeb: Model-Based Reinforcement Learning of Web Agents", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2602.01576v2", "archive": "arXiv", "archive_location": "2602.01576", "author": [ { "literal": "Woosung Koh" }, { "literal": "Sungjun Han" }, { "literal": "Segyu Lee" }, { "literal": "Se-Young Yun" }, { "literal": "Jamin Shin" } ], "citation-key": "arxiv_2602_01576", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7c29d1404b02c4f5ef2cdaf78bdb0f9062b1b85ec1a154408bc8f49446c28d08", "submitted_at": "2026-02-02T03:12:16Z", "updated_at": "2026-05-23T02:41:44Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2602.01576v2" }, "canonical_source_url": "https://arxiv.org/abs/2602.01576", "catalog_id": "arxiv:2602.01576", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-02", "identifiers": { "arxiv": "2602.01576" }, "record_updated_at": "2026-05-23" }, "genre": "preprint", "id": "arxiv:2602.01576", "issued": { "date-parts": [ [ 2026, 2, 2 ] ] }, "note": "First published: 2026-02-02; Recorded arXiv version: v2; Recorded version updated: 2026-05-23T02:41:44Z.", "title": "Generative Visual Code Mobile World Models", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2602.01725v1", "archive": "arXiv", "archive_location": "2602.01725", "author": [ { "literal": "Yurun Chen" }, { "literal": "Zeyi Liao" }, { "literal": "Ping Yin" }, { "literal": "Taotao Xie" }, { "literal": "Keting Yin" }, { "literal": "Shengyu Zhang" } ], "citation-key": "arxiv_2602_01725", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d1a6f98c0ab0a221c169796d9680e4b2a7bf7a0775c0493254f47d5e0a9b3c4e", "submitted_at": "2026-02-02T07:04:06Z", "updated_at": "2026-02-02T07:04:06Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.01725v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.01725", "catalog_id": "arxiv:2602.01725", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-02", "identifiers": { "arxiv": "2602.01725" }, "record_updated_at": "2026-02-02" }, "genre": "preprint", "id": "arxiv:2602.01725", "issued": { "date-parts": [ [ 2026, 2, 2 ] ] }, "note": "First published: 2026-02-02; Recorded arXiv version: v1; Recorded version updated: 2026-02-02T07:04:06Z.", "title": "SafePred: A Predictive Guardrail for Computer-Using Agents via World Models", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.09007v3", "archive": "arXiv", "archive_location": "2602.09007", "author": [ { "literal": "Haodong Li" }, { "literal": "Jingwei Wu" }, { "literal": "Quan Sun" }, { "literal": "Guopeng Li" }, { "literal": "Juanxi Tian" }, { "literal": "Ziyu Guo" }, { "literal": "Donghao Zhou" }, { "literal": "Tianfei Ren" }, { "literal": "Huanyu Zhang" }, { "literal": "Yanlin Lai" }, { "literal": "Ruichuan An" }, { "literal": "Hongbo Peng" }, { "literal": "Yuhong Dai" }, { "literal": "Jia Wang" }, { "literal": "Ziyang Meng" }, { "literal": "Zheng Ge" }, { "literal": "Xiangyu Zhang" }, { "literal": "Daxin Jiang" }, { "literal": "Pheng-Ann Heng" } ], "citation-key": "arxiv_2602_09007", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "43a01e0eb848a57a84767836d2c3c982bbf6094d22a3e70652dd42af52760bc5", "submitted_at": "2026-02-09T18:52:02Z", "updated_at": "2026-09-26T18:28:57Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2602.09007v3" }, "canonical_source_url": "https://arxiv.org/abs/2602.09007", "catalog_id": "arxiv:2602.09007", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-09", "identifiers": { "arxiv": "2602.09007" }, "record_updated_at": "2026-09-26" }, "genre": "preprint", "id": "arxiv:2602.09007", "issued": { "date-parts": [ [ 2026, 2, 9 ] ] }, "note": "First published: 2026-02-09; Recorded arXiv version: v3; Recorded version updated: 2026-09-26T18:28:57Z.", "title": "GUI-GenBench: Evaluating Image Generation Models as Interactive GUI Environments", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2602.09856v1", "archive": "arXiv", "archive_location": "2602.09856", "author": [ { "literal": "Yuhao Zheng" }, { "literal": "Li'an Zhong" }, { "literal": "Yi Wang" }, { "literal": "Rui Dai" }, { "literal": "Kaikui Liu" }, { "literal": "Xiangxiang Chu" }, { "literal": "Linyuan Lv" }, { "literal": "Philip Torr" }, { "literal": "Kevin Qinghong Lin" } ], "citation-key": "arxiv_2602_09856", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "55287e2fe8a5e94671e4aab8e9d4a907ba9b6c83306d9b3f61b74adccd5c5059", "submitted_at": "2026-02-10T14:56:19Z", "updated_at": "2026-02-10T14:56:19Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.09856v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.09856", "catalog_id": "arxiv:2602.09856", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-10", "identifiers": { "arxiv": "2602.09856" }, "record_updated_at": "2026-02-10" }, "genre": "preprint", "id": "arxiv:2602.09856", "issued": { "date-parts": [ [ 2026, 2, 10 ] ] }, "note": "First published: 2026-02-10; Recorded arXiv version: v1; Recorded version updated: 2026-02-10T14:56:19Z.", "title": "Code2World: A GUI World Model via Renderable Code Generation", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.14721v1", "archive": "arXiv", "archive_location": "2602.14721", "author": [ { "literal": "Zikai Xiao" }, { "literal": "Jianhong Tu" }, { "literal": "Chuhang Zou" }, { "literal": "Yuxin Zuo" }, { "literal": "Zhi Li" }, { "literal": "Peng Wang" }, { "literal": "Bowen Yu" }, { "literal": "Fei Huang" }, { "literal": "Junyang Lin" }, { "literal": "Zuozhu Liu" } ], "citation-key": "arxiv_2602_14721", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "2dca0e4219a788205bbb060911d0f004d1db4cf2ff8a4962c04fd5777ea194d7", "submitted_at": "2026-02-16T13:06:49Z", "updated_at": "2026-02-16T13:06:49Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.14721v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.14721", "catalog_id": "arxiv:2602.14721", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-16", "identifiers": { "arxiv": "2602.14721" }, "record_updated_at": "2026-02-16" }, "genre": "preprint", "id": "arxiv:2602.14721", "issued": { "date-parts": [ [ 2026, 2, 16 ] ] }, "note": "First published: 2026-02-16; Recorded arXiv version: v1; Recorded version updated: 2026-02-16T13:06:49Z.", "title": "WebWorld: A Large-Scale World Model for Web Agent Training", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2602.17365v1", "archive": "arXiv", "archive_location": "2602.17365", "author": [ { "literal": "Yiming Guan" }, { "literal": "Rui Yu" }, { "literal": "John Zhang" }, { "literal": "Lu Wang" }, { "literal": "Chaoyun Zhang" }, { "literal": "Liqun Li" }, { "literal": "Bo Qiao" }, { "literal": "Si Qin" }, { "literal": "He Huang" }, { "literal": "Fangkai Yang" }, { "literal": "Pu Zhao" }, { "literal": "Lukas Wutschitz" }, { "literal": "Samuel Kessler" }, { "literal": "Huseyin A Inan" }, { "literal": "Robert Sim" }, { "literal": "Saravan Rajmohan" }, { "literal": "Qingwei Lin" }, { "literal": "Dongmei Zhang" } ], "citation-key": "arxiv_2602_17365", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "3d2237dd43f4c876ba69b68c1871ca3efd3aa501e93c86655eb2de6d9f35d2e8", "submitted_at": "2026-02-19T13:48:29Z", "updated_at": "2026-02-19T13:48:29Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2602.17365v1" }, "canonical_source_url": "https://arxiv.org/abs/2602.17365", "catalog_id": "arxiv:2602.17365", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-19", "identifiers": { "arxiv": "2602.17365" }, "record_updated_at": "2026-02-19" }, "genre": "preprint", "id": "arxiv:2602.17365", "issued": { "date-parts": [ [ 2026, 2, 19 ] ] }, "note": "First published: 2026-02-19; Recorded arXiv version: v1; Recorded version updated: 2026-02-19T13:48:29Z.", "title": "Computer-Using World Model", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2604.02345v1", "archive": "arXiv", "archive_location": "2604.02345", "author": [ { "literal": "Mengzhou Wu" }, { "literal": "Yuzhe Guo" }, { "literal": "Yuan Cao" }, { "literal": "Haochuan Lu" }, { "literal": "Songhe Zhu" }, { "literal": "Pingzhe Qu" }, { "literal": "Xin Chen" }, { "literal": "Kang Qin" }, { "literal": "Zhongpu Wang" }, { "literal": "Xiaode Zhang" }, { "literal": "Xinyi Wang" }, { "literal": "Wei Dai" }, { "literal": "Gang Cao" }, { "literal": "Yuetang Deng" }, { "literal": "Zhi Gong" }, { "literal": "Dezhi Ran" }, { "literal": "Linyi Li" }, { "literal": "Wei Yang" }, { "literal": "Tao Xie" } ], "citation-key": "arxiv_2604_02345", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "bac86c2ff2bf18feb3edfbe76285d33718d0c6d9564aff5a9d62f8778cdc5147", "submitted_at": "2026-02-11T17:02:38Z", "updated_at": "2026-02-11T17:02:38Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2604.02345v1" }, "canonical_source_url": "https://arxiv.org/abs/2604.02345", "catalog_id": "arxiv:2604.02345", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-02-11", "identifiers": { "arxiv": "2604.02345" }, "record_updated_at": "2026-02-11" }, "genre": "preprint", "id": "arxiv:2604.02345", "issued": { "date-parts": [ [ 2026, 2, 11 ] ] }, "note": "First published: 2026-02-11; Recorded arXiv version: v1; Recorded version updated: 2026-02-11T17:02:38Z.", "title": "UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2605.10347v2", "archive": "arXiv", "archive_location": "2605.10347", "author": [ { "literal": "Weikai Xu" }, { "literal": "Kun Huang" }, { "literal": "Yunren Feng" }, { "literal": "Jiaxing Li" }, { "literal": "Yuhan Chen" }, { "literal": "Yuxuan Liu" }, { "literal": "Zhizheng Jiang" }, { "literal": "Heng Qu" }, { "literal": "Pengzhi Gao" }, { "literal": "Wei Liu" }, { "literal": "Jian Luan" }, { "literal": "Xiaolin Hu" }, { "literal": "Bo An" } ], "citation-key": "arxiv_2605_10347", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4374ec1b7c44804bb78ea56bd0aa3214083419f37780d79c5fcfb68468727bbf", "submitted_at": "2026-05-11T10:49:31Z", "updated_at": "2026-05-22T05:43:30Z", "version": 2, "versioned_url": "https://arxiv.org/abs/2605.10347v2" }, "canonical_source_url": "https://arxiv.org/abs/2605.10347", "catalog_id": "arxiv:2605.10347", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-05-11", "identifiers": { "arxiv": "2605.10347" }, "record_updated_at": "2026-05-22" }, "genre": "preprint", "id": "arxiv:2605.10347", "issued": { "date-parts": [ [ 2026, 5, 11 ] ] }, "note": "First published: 2026-05-11; Recorded arXiv version: v2; Recorded version updated: 2026-05-22T05:43:30Z.", "title": "How Mobile World Model Guides GUI Agents?", "type": "article", "version": "2" }, { "URL": "https://arxiv.org/abs/2607.15550v3", "archive": "arXiv", "archive_location": "2607.15550", "author": [ { "literal": "Xue Yu" }, { "literal": "Bo Yuan" }, { "literal": "Kailin Zhao" }, { "literal": "Pengshuai Yang" }, { "literal": "Hong Hu" }, { "literal": "Junlan Feng" } ], "citation-key": "arxiv_2607_15550", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6a15963a7fb4dfd488f0e79732d9ea0c9a03d43c1e3d5e50dd1ee8e00f1072be", "submitted_at": "2026-07-17T01:45:54Z", "updated_at": "2026-09-02T01:49:21Z", "version": 3, "versioned_url": "https://arxiv.org/abs/2607.15550v3" }, "canonical_source_url": "https://arxiv.org/abs/2607.15550", "catalog_id": "arxiv:2607.15550", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-17", "identifiers": { "arxiv": "2607.15550" }, "record_updated_at": "2026-09-02" }, "genre": "preprint", "id": "arxiv:2607.15550", "issued": { "date-parts": [ [ 2026, 7, 17 ] ] }, "note": "First published: 2026-07-17; Recorded arXiv version: v3; Recorded version updated: 2026-09-02T01:49:21Z.", "title": "SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction", "type": "article", "version": "3" }, { "URL": "https://arxiv.org/abs/2607.17050v1", "archive": "arXiv", "archive_location": "2607.17050", "author": [ { "literal": "Yaohan Yang" }, { "literal": "Minglei Shi" }, { "literal": "Borui Zhang" }, { "literal": "Jie Zhou" }, { "literal": "Jiwen Lu" } ], "citation-key": "arxiv_2607_17050", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "6488798626abbec89ca739a0c5d188ae440484eb59b3be11f2b319ce742b22ec", "submitted_at": "2026-07-19T03:29:08Z", "updated_at": "2026-07-19T03:29:08Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2607.17050v1" }, "canonical_source_url": "https://arxiv.org/abs/2607.17050", "catalog_id": "arxiv:2607.17050", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-19", "identifiers": { "arxiv": "2607.17050" }, "record_updated_at": "2026-07-19" }, "genre": "preprint", "id": "arxiv:2607.17050", "issued": { "date-parts": [ [ 2026, 7, 19 ] ] }, "note": "First published: 2026-07-19; Recorded arXiv version: v1; Recorded version updated: 2026-07-19T03:29:08Z.", "title": "EvoGUI: An Evolution-Aware Benchmark for GUI State-Transition Understanding", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2607.24112v1", "archive": "arXiv", "archive_location": "2607.24112", "author": [ { "literal": "Xiangyan Liu" }, { "literal": "Kaixin Li" }, { "literal": "Haonan Wang" }, { "literal": "Biao Wu" }, { "literal": "Meng Fang" }, { "literal": "Longxu Dou" }, { "literal": "Chao Du" }, { "literal": "Michael Qizhe Shieh" }, { "literal": "Tianyu Pang" } ], "citation-key": "arxiv_2607_24112", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "4651964cbe45e4d740ed8f789753f82ae808e442d82c6598e7b3c997c09453c3", "submitted_at": "2026-07-27T07:54:08Z", "updated_at": "2026-07-27T07:54:08Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2607.24112v1" }, "canonical_source_url": "https://arxiv.org/abs/2607.24112", "catalog_id": "arxiv:2607.24112", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-07-27", "identifiers": { "arxiv": "2607.24112" }, "record_updated_at": "2026-07-27" }, "genre": "preprint", "id": "arxiv:2607.24112", "issued": { "date-parts": [ [ 2026, 7, 27 ] ] }, "note": "First published: 2026-07-27; Recorded arXiv version: v1; Recorded version updated: 2026-07-27T07:54:08Z.", "title": "Scaling GUI Agents with Visual State Transitions", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2608.05891v1", "archive": "arXiv", "archive_location": "2608.05891", "author": [ { "literal": "Weikai Xu" }, { "literal": "Yunren Feng" }, { "literal": "Haoxiang Lei" }, { "literal": "Kun Huang" }, { "literal": "Yuxuan Liu" }, { "literal": "Kang Zhao" }, { "literal": "Xiaolin Hu" }, { "literal": "Shuo Shang" }, { "literal": "Bo An" } ], "citation-key": "arxiv_2608_05891", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ce37dd8217afbaa07ddea25c0daf78cdbfb449851ca6ab17b7f3ecacd451eb2f", "submitted_at": "2026-08-06T11:15:41Z", "updated_at": "2026-08-06T11:15:41Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.05891v1" }, "canonical_source_url": "https://arxiv.org/abs/2608.05891", "catalog_id": "arxiv:2608.05891", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-06", "identifiers": { "arxiv": "2608.05891" }, "record_updated_at": "2026-08-06" }, "genre": "preprint", "id": "arxiv:2608.05891", "issued": { "date-parts": [ [ 2026, 8, 6 ] ] }, "note": "First published: 2026-08-06; Recorded arXiv version: v1; Recorded version updated: 2026-08-06T11:15:41Z.", "title": "AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2608.27508v1", "archive": "arXiv", "archive_location": "2608.27508", "author": [ { "literal": "Yu Han" }, { "literal": "Tianwen Qian" } ], "citation-key": "arxiv_2608_27508", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "576702fae164cbcb4adc86a81115487aae7e1c40cf07a1ecf3ef7c4c7e822c3b", "submitted_at": "2026-08-27T07:09:28Z", "updated_at": "2026-08-27T07:09:28Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2608.27508v1" }, "canonical_source_url": "https://arxiv.org/abs/2608.27508", "catalog_id": "arxiv:2608.27508", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-08-27", "identifiers": { "arxiv": "2608.27508" }, "record_updated_at": "2026-08-27" }, "genre": "preprint", "id": "arxiv:2608.27508", "issued": { "date-parts": [ [ 2026, 8, 27 ] ] }, "note": "First published: 2026-08-27; Recorded arXiv version: v1; Recorded version updated: 2026-08-27T07:09:28Z.", "title": "WM-R1: Training GUI Agents to Reason and leverage World Models with Reinforcement Learning", "type": "article", "version": "1" }, { "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/2609.02885v1", "archive": "arXiv", "archive_location": "2609.02885", "author": [ { "literal": "Kelvin Li" }, { "literal": "Dhruv Pendharkar" }, { "literal": "Anish Pahilajani" }, { "literal": "Chuyi Shang" }, { "literal": "Leon Oks" }, { "literal": "Leonid Karlinsky" }, { "literal": "Rogerio Feris" }, { "literal": "Trevor Darrell" }, { "literal": "Roei Herzig" } ], "citation-key": "arxiv_2609_02885", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "8703474cb4f577b307731cf1a986f76f800470fde625b6ca4b3569d30e74f903", "submitted_at": "2026-09-02T17:59:40Z", "updated_at": "2026-09-02T17:59:40Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.02885v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.02885", "catalog_id": "arxiv:2609.02885", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-02", "identifiers": { "arxiv": "2609.02885" }, "record_updated_at": "2026-09-02" }, "genre": "preprint", "id": "arxiv:2609.02885", "issued": { "date-parts": [ [ 2026, 9, 2 ] ] }, "note": "First published: 2026-09-02; Recorded arXiv version: v1; Recorded version updated: 2026-09-02T17:59:40Z.", "title": "Discriminative World Models for Web Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2609.32679v1", "archive": "arXiv", "archive_location": "2609.32679", "author": [ { "literal": "Dongsheng Liu" }, { "literal": "Chao Jin" }, { "literal": "Wenkui Yang" }, { "literal": "Hejin Wang" }, { "literal": "Junwei Yang" }, { "literal": "Zeren Zhang" }, { "literal": "Ziwei Chen" }, { "literal": "Huaibo Huang" }, { "literal": "Jie Cao" }, { "literal": "Ran He" } ], "citation-key": "arxiv_2609_32679", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "d641819d168eedc07270607da33f3197c15f2f90cf99f538c3839eed506f3308", "submitted_at": "2026-09-26T14:35:45Z", "updated_at": "2026-09-26T14:35:45Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2609.32679v1" }, "canonical_source_url": "https://arxiv.org/abs/2609.32679", "catalog_id": "arxiv:2609.32679", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-09-26", "identifiers": { "arxiv": "2609.32679" }, "record_updated_at": "2026-09-26" }, "genre": "preprint", "id": "arxiv:2609.32679", "issued": { "date-parts": [ [ 2026, 9, 26 ] ] }, "note": "First published: 2026-09-26; Recorded arXiv version: v1; Recorded version updated: 2026-09-26T14:35:45Z.", "title": "The GUI Is Not the State: Diagnosing State Aliasing in GUI World Models", "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/2610.01215v1", "archive": "arXiv", "archive_location": "2610.01215", "author": [ { "literal": "Cheng Yang" }, { "literal": "Yifan Wu" }, { "literal": "Yutao Huang" }, { "literal": "Zhaohua Zhang" }, { "literal": "Beiduo Chen" }, { "literal": "Muxi Chen" }, { "literal": "Chenchen Zhao" }, { "literal": "Hexuan Deng" }, { "literal": "Haolin Yang" }, { "literal": "Geyuan Zhu" }, { "literal": "Sa Zhu" }, { "literal": "Jianhuan Zhuo" }, { "literal": "Qiuyong Xiao" }, { "literal": "Jianhao Ruan" }, { "literal": "Yiran Peng" }, { "literal": "Jiayi Zhang" }, { "literal": "Tian Ye" }, { "literal": "Xinlei Yu" }, { "literal": "Tianwen Jiang" }, { "literal": "Jihong Zhang" }, { "literal": "Yuyu Luo" } ], "citation-key": "arxiv_2610_01215", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "ecd40b78c6de41abb442705b993aad8ebf7b35741536a11e00ebbd60140d1f18", "submitted_at": "2026-10-01T07:22:53Z", "updated_at": "2026-10-01T07:22:53Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.01215v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.01215", "catalog_id": "arxiv:2610.01215", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-01", "identifiers": { "arxiv": "2610.01215" }, "record_updated_at": "2026-10-01" }, "genre": "preprint", "id": "arxiv:2610.01215", "issued": { "date-parts": [ [ 2026, 10, 1 ] ] }, "note": "First published: 2026-10-01; Recorded arXiv version: v1; Recorded version updated: 2026-10-01T07:22:53Z.", "title": "AutoGUIWorld: Image Generators as Visual World Models for GUI Agent", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.02542v1", "archive": "arXiv", "archive_location": "2610.02542", "author": [ { "literal": "Dhananjay Ashok" }, { "literal": "Shantanu Agarwal" }, { "literal": "Vivek Datla" }, { "literal": "Jonathan May" }, { "literal": "Alfy Samuel" } ], "citation-key": "arxiv_2610_02542", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "35ded32e7bac9a875a0fa41efad43fed5fb0aab54fade5cfc2a0628b1e666587", "submitted_at": "2026-10-01T22:30:08Z", "updated_at": "2026-10-01T22:30:08Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.02542v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.02542", "catalog_id": "arxiv:2610.02542", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "adjacent", "first_published_at": "2026-10-01", "identifiers": { "arxiv": "2610.02542" }, "record_updated_at": "2026-10-01" }, "genre": "preprint", "id": "arxiv:2610.02542", "issued": { "date-parts": [ [ 2026, 10, 1 ] ] }, "note": "First published: 2026-10-01; Recorded arXiv version: v1; Recorded version updated: 2026-10-01T22:30:08Z.", "title": "How To Train Your World Model: Fine-tuning vs RAG for LM-based World Modeling", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.05861v1", "archive": "arXiv", "archive_location": "2610.05861", "author": [ { "literal": "Yongxin Ning" }, { "literal": "Runliang Niu" }, { "literal": "Qianli Xing" }, { "literal": "Zhiyi Duan" }, { "literal": "Qingzu He" }, { "literal": "Pan Wang" }, { "literal": "Qi Wang" } ], "citation-key": "arxiv_2610_05861", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "43845ad64843a0b019c1988d4ba861eccee3c48a7b2c09d0bae7794e5e86347a", "submitted_at": "2026-10-05T06:28:58Z", "updated_at": "2026-10-05T06:28:58Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.05861v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.05861", "catalog_id": "arxiv:2610.05861", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-05", "identifiers": { "arxiv": "2610.05861" }, "record_updated_at": "2026-10-05" }, "genre": "preprint", "id": "arxiv:2610.05861", "issued": { "date-parts": [ [ 2026, 10, 5 ] ] }, "note": "First published: 2026-10-05; Recorded arXiv version: v1; Recorded version updated: 2026-10-05T06:28:58Z.", "title": "Imagine to Act: High-Fidelity Data Synthesis via Image Editing World Model for Scalable GUI Agent Training", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.08773v1", "archive": "arXiv", "archive_location": "2610.08773", "author": [ { "literal": "Sarim Hashmi" }, { "literal": "Mukul Ranjan" }, { "literal": "Kshitij Mishra" }, { "literal": "Mikhail Kuznetsov" }, { "literal": "Praneeth Vepakomma" }, { "literal": "Nils Lukas" } ], "citation-key": "arxiv_2610_08773", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "7113025e0dfd784d6994108c24681000625b13598e33ad0e4324e90fd2832c19", "submitted_at": "2026-10-06T17:56:43Z", "updated_at": "2026-10-06T17:56:43Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.08773v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.08773", "catalog_id": "arxiv:2610.08773", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-06", "identifiers": { "arxiv": "2610.08773" }, "record_updated_at": "2026-10-06" }, "genre": "preprint", "id": "arxiv:2610.08773", "issued": { "date-parts": [ [ 2026, 10, 6 ] ] }, "note": "First published: 2026-10-06; Recorded arXiv version: v1; Recorded version updated: 2026-10-06T17:56:43Z.", "title": "AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.11942v1", "archive": "arXiv", "archive_location": "2610.11942", "author": [ { "literal": "Jiaming Zhang" }, { "literal": "Xuan Wang" }, { "literal": "Fuyao Zhang" }, { "literal": "Yang Cao" }, { "literal": "Lingjuan Lyu" }, { "literal": "Wei Yang Bryan Lim" } ], "citation-key": "arxiv_2610_11942", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "53120f960c7b98e87210c93ac661a2e397b858cc9f211786b0f8233fa61c6dd3", "submitted_at": "2026-10-08T13:33:23Z", "updated_at": "2026-10-08T13:33:23Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.11942v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.11942", "catalog_id": "arxiv:2610.11942", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-08", "identifiers": { "arxiv": "2610.11942" }, "record_updated_at": "2026-10-08" }, "genre": "preprint", "id": "arxiv:2610.11942", "issued": { "date-parts": [ [ 2026, 10, 8 ] ] }, "note": "First published: 2026-10-08; Recorded arXiv version: v1; Recorded version updated: 2026-10-08T13:33:23Z.", "title": "Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.14228v1", "archive": "arXiv", "archive_location": "2610.14228", "author": [ { "literal": "Seungjun Yu" }, { "literal": "Hojun Choi" }, { "literal": "Seojeong Park" }, { "literal": "Jaeyo Shin" }, { "literal": "Hyunjung Shim" } ], "citation-key": "arxiv_2610_14228", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "191e88c19124ddaddc2fed2f0e3f8e197a4c0c7f8adbc3997c056d3333754042", "submitted_at": "2026-10-09T18:45:11Z", "updated_at": "2026-10-09T18:45:11Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.14228v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.14228", "catalog_id": "arxiv:2610.14228", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-09", "identifiers": { "arxiv": "2610.14228" }, "record_updated_at": "2026-10-09" }, "genre": "preprint", "id": "arxiv:2610.14228", "issued": { "date-parts": [ [ 2026, 10, 9 ] ] }, "note": "First published: 2026-10-09; Recorded arXiv version: v1; Recorded version updated: 2026-10-09T18:45:11Z.", "title": "Latent World Action Model for GUI Agents", "type": "article", "version": "1" }, { "URL": "https://arxiv.org/abs/2610.24372v1", "archive": "arXiv", "archive_location": "2610.24372", "author": [ { "literal": "Sizhe Tang" }, { "literal": "Hanhan Zhou" }, { "literal": "Jeffrey Svajlenko" }, { "literal": "Rashmi Gangadharaiah" } ], "citation-key": "arxiv_2610_24372", "custom": { "arxiv_snapshot": { "abstract_hash_method": "sha256-utf8-whitespace-collapsed-v1", "abstract_sha256": "9d6808cf26a609b50b7835ae3ecece0a13580aafcd589823f0b1eeff54732f69", "submitted_at": "2026-10-17T02:03:20Z", "updated_at": "2026-10-17T02:03:20Z", "version": 1, "versioned_url": "https://arxiv.org/abs/2610.24372v1" }, "canonical_source_url": "https://arxiv.org/abs/2610.24372", "catalog_id": "arxiv:2610.24372", "catalog_kind": "paper", "catalog_review_status": "curated", "catalog_scope": "core", "first_published_at": "2026-10-17", "identifiers": { "arxiv": "2610.24372" }, "record_updated_at": "2026-10-17" }, "genre": "preprint", "id": "arxiv:2610.24372", "issued": { "date-parts": [ [ 2026, 10, 17 ] ] }, "note": "First published: 2026-10-17; Recorded arXiv version: v1; Recorded version updated: 2026-10-17T02:03:20Z.", "title": "Beyond Next-Screen Prediction: The Decision Value of GUI World Models", "type": "article", "version": "1" } ]