{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T04:07:46Z","timestamp":1779422866790,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T00:00:00Z","timestamp":1779753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,26]]},"DOI":"10.1145\/3786335.3813203","type":"proceedings-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T03:16:22Z","timestamp":1779419782000},"page":"1172-1178","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["cotomi Act: Learning to Automate Work by Watching You"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4045-7350","authenticated-orcid":false,"given":"Masafumi","family":"Oyamada","sequence":"first","affiliation":[{"name":"NEC Corporation, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9653-8523","authenticated-orcid":false,"given":"Kunihiro","family":"Takeoka","sequence":"additional","affiliation":[{"name":"NEC Corporation, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5608-0719","authenticated-orcid":false,"given":"Kosuke","family":"Akimoto","sequence":"additional","affiliation":[{"name":"NEC Corporation, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2869-6218","authenticated-orcid":false,"given":"Ryoma","family":"Obara","sequence":"additional","affiliation":[{"name":"NEC Corporation, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1176-9256","authenticated-orcid":false,"given":"Masafumi","family":"Enomoto","sequence":"additional","affiliation":[{"name":"NEC Corporation, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2537-4984","authenticated-orcid":false,"given":"Haochen","family":"Zhang","sequence":"additional","affiliation":[{"name":"NEC Corporation, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0410-227X","authenticated-orcid":false,"given":"Daichi","family":"Haraguchi","sequence":"additional","affiliation":[{"name":"NEC Corporation, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2379-0434","authenticated-orcid":false,"given":"Takuya","family":"Tamura","sequence":"additional","affiliation":[{"name":"NEC Corporation, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,26]]},"reference":[{"key":"e_1_3_3_2_2_2","volume-title":"International Conference on Learning Representations","author":"Agashe Saaket","year":"2025","unstructured":"Saaket Agashe, Jiuzhou Han, Shuyu Gan, Jiachen Yang, Ang Li, and Xin\u00a0Eric Wang. 2025. Agent S: An Open Agentic Framework that Uses Computers Like a Human. In International Conference on Learning Representations. OpenReview.net, Singapore, 24\u00a0pages."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Robert\u00a0W. Andrews J.\u00a0Mason Lilly Divya Srivastava and Karen\u00a0M. Feigh. 2023. The Role of Shared Mental Models in Human-AI Teams: A Theoretical Review. Theoretical Issues in Ergonomics Science 24 2 (2023) 129\u2013175.","DOI":"10.1080\/1463922X.2022.2061080"},{"key":"e_1_3_3_2_4_2","unstructured":"Anthropic. 2024. Introducing Computer Use a New Claude 3.5 Sonnet and Claude 3.5 Haiku. https:\/\/www.anthropic.com\/news\/3-5-models-and-computer-use."},{"key":"e_1_3_3_2_5_2","unstructured":"Alexandre Drouin Maxime Gasse Massimo Caccia Issam\u00a0H. Laradji Manuel Del\u00a0Verme Tom Marty L\u00e9o Boisvert Megh Thakkar Quentin Cappart David V\u00e1zquez Nicolas Chapados and Alexandre Lacoste. 2024. WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.07718 (2024) 27\u00a0pages."},{"key":"e_1_3_3_2_6_2","volume-title":"Workshop on Scaling Environments for Agents","author":"El\u00a0hattami Amine","year":"2025","unstructured":"Amine El\u00a0hattami, Megh Thakkar, Nicolas Chapados, and Christopher Pal. 2025. WebArena Verified: Reliable Evaluation for Web Agents. In Workshop on Scaling Environments for Agents. https:\/\/openreview.net\/forum?id=94tlGxmqkN"},{"key":"e_1_3_3_2_7_2","unstructured":"Masafumi Enomoto Ryoma Obara Haochen Zhang and Masafumi Oyamada. 2026. Read More Think More: Revisiting Observation Reduction for Web Agents. arxiv:https:\/\/arXiv.org\/abs\/2604.01535\u00a0[cs.CL]"},{"key":"e_1_3_3_2_8_2","unstructured":"Google. 2024. Project Mariner. https:\/\/deepmind.google\/technologies\/project-mariner\/."},{"key":"e_1_3_3_2_9_2","unstructured":"Yuyu Guo Wenjie Yang Siyuan Yang Ziyang Liu Cheng Chen Yuan Wei Yun Hu Yang Huang Guoliang Hao Dongsheng Yuan Jianming Wang Xin Chen Hang Yu Lei Lei and Peng Di. 2026. OpAgent: Operator Agent for Web Navigation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2602.13559 (2026)."},{"key":"e_1_3_3_2_10_2","volume-title":"International Conference on Learning Representations","author":"Gur Izzeddin","year":"2024","unstructured":"Izzeddin Gur, Hiroki Furuta, Austin Huang, Mustafa Safdari, Yutaka Matsuo, Douglas Eck, and Aleksandra Faust. 2024. A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis. In International Conference on Learning Representations. OpenReview.net, Vienna, Austria, 23\u00a0pages."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/302979.303030"},{"key":"e_1_3_3_2_12_2","volume-title":"International Conference on Learning Representations","author":"Komiyama Junpei","year":"2026","unstructured":"Junpei Komiyama, Daisuke Oba, and Masafumi Oyamada. 2026. Best-of-\u221e : Asymptotic Performance of Test-Time LLM Ensembling. In International Conference on Learning Representations. OpenReview.net. arXiv:https:\/\/arXiv.org\/abs\/2509.21091."},{"key":"e_1_3_3_2_13_2","volume-title":"Advances in Neural Information Processing Systems","author":"Light Jonathan","year":"2025","unstructured":"Jonathan Light, Wei Cheng, Benjamin Riviere, Wu Yue, Masafumi Oyamada, Mengdi Wang, Yisong Yue, Santiago Paternain, and Haifeng Chen. 2025. DISC: Dynamic Decomposition Improves LLM Inference Scaling. In Advances in Neural Information Processing Systems. Curran Associates. arXiv:https:\/\/arXiv.org\/abs\/2502.16706."},{"key":"e_1_3_3_2_14_2","unstructured":"NEC. 2025. NEC Develops Agent Technology \u201ccotomi Act\u201d for Automating Web-Based Knowledge Work by Learning and Leveraging Tacit Knowledge. https:\/\/jpn.nec.com\/press\/202508\/20250827_02.html."},{"key":"e_1_3_3_2_15_2","unstructured":"OpenAI. 2025. Computer-Using Agent. https:\/\/openai.com\/index\/computer-using-agent\/."},{"key":"e_1_3_3_2_16_2","unstructured":"Charles Packer Sarah Wooders Kevin Lin Vivian Fang Shishir\u00a0G. Patil Ion Stoica and Joseph\u00a0E. Gonzalez. 2023. MemGPT: Towards LLMs as Operating Systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.08560 (2023) 16\u00a0pages."},{"key":"e_1_3_3_2_17_2","unstructured":"Noah Shinn Federico Cassano Edward Berman Ashwin Gopinath Karthik Narasimhan and Shunyu Yao. 2023. Reflexion: Language Agents with Verbal Reinforcement Learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.11366 (2023) 10\u00a0pages."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i47.41485"},{"key":"e_1_3_3_2_19_2","volume-title":"Proceedings of the Conference on Language Modeling (COLM)","author":"Sodhi Paloma","year":"2024","unstructured":"Paloma Sodhi, S.R.K. Branavan, Yoav Artzi, and Ryan McDonald. 2024. SteP: Stacked LLM Policies for Web Actions. In Proceedings of the Conference on Language Modeling (COLM). arxiv:https:\/\/arXiv.org\/abs\/2310.03720"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Susan\u00a0Leigh Star and James\u00a0R. Griesemer. 1989. Institutional Ecology \u201cTranslations \u201d and Boundary Objects: Amateurs and Professionals in Berkeley\u2019s Museum of Vertebrate Zoology 1907\u201339. Social Studies of Science 19 3 (1989) 387\u2013420.","DOI":"10.1177\/030631289019003001"},{"key":"e_1_3_3_2_21_2","unstructured":"Guanzhi Wang Yuqi Xie Yunfan Jiang Ajay Mandlekar Chaowei Xiao Yuke Zhu Linxi Fan and Anima Anandkumar. 2023. Voyager: An Open-Ended Embodied Agent with Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.16291 (2023) 22\u00a0pages."},{"key":"e_1_3_3_2_22_2","unstructured":"Zora\u00a0Zhiruo Wang Jiayuan Mao Daniel Fried and Graham Neubig. 2024. Agent Workflow Memory. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.07429 (2024) 16\u00a0pages."},{"key":"e_1_3_3_2_23_2","volume-title":"Advances in Neural Information Processing Systems","author":"Xie Tianbao","year":"2024","unstructured":"Tianbao Xie, Danyang Zhang, Jixuan Chen, Xiaochuan Li, Siheng Zhao, Ruisheng Cao, Toh\u00a0Jing Hua, Zhoujun Cheng, Dongchan Shin, Fangyu Lei, Yitao Liu, Yiheng Xu, Shuyan Zhou, Silvio Savarese, Caiming Xiong, Victor Zhong, and Tao Yu. 2024. OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments. In Advances in Neural Information Processing Systems. Curran Associates, Vancouver, Canada, 37\u00a0pages."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.902"},{"key":"e_1_3_3_2_25_2","volume-title":"Proceedings of the Conference on Language Modeling (COLM)","author":"Xue Tianci","year":"2025","unstructured":"Tianci Xue, Weijian Qi, Tianneng Shi, Chan\u00a0Hee Song, Boyu Gou, Dawn Song, Huan Sun, and Yu Su. 2025. An Illusion of Progress? Assessing the Current State of Web Agents. In Proceedings of the Conference on Language Modeling (COLM). 15\u00a0pages."},{"key":"e_1_3_3_2_26_2","volume-title":"International Conference on Learning Representations","author":"Yang Ke","year":"2025","unstructured":"Ke Yang, Yao Liu, Sapana Chaudhary, Rasool Fakoor, Pratik Chaudhari, George Karypis, and Huzefa Rangwala. 2025. AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents. In International Conference on Learning Representations. OpenReview.net, Singapore, 21\u00a0pages."},{"key":"e_1_3_3_2_27_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_28_2","volume-title":"WebArena Mod","author":"Zhang Haochen","year":"2025","unstructured":"Haochen Zhang, Masafumi Enomoto, Ryoma Obara, Kunihiro Takeoka, and Masafumi Oyamada. 2025. WebArena Mod. https:\/\/github.com\/nec-research-labs\/WebArena-Mod"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29936"},{"key":"e_1_3_3_2_30_2","unstructured":"Boyuan Zheng Boyu Gou Jihyung Kil Huan Sun and Yu Su. 2024. GPT-4V(ision) is a Generalist Web Agent if Grounded. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.01614 (2024) 18\u00a0pages."},{"key":"e_1_3_3_2_31_2","volume-title":"International Conference on Learning Representations","author":"Zhou Shuyan","year":"2024","unstructured":"Shuyan Zhou, Frank\u00a0F. Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, and Graham Neubig. 2024. WebArena: A Realistic Web Environment for Building Autonomous Agents. In International Conference on Learning Representations. OpenReview.net, Vienna, Austria, 26\u00a0pages."}],"event":{"name":"CAIS '26: ACM Conference on AI and Agentic Systems","location":"San Jose CA USA","acronym":"CAIS '26"},"container-title":["Proceedings of the ACM Conference on AI and Agentic Systems"],"original-title":[],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T03:27:00Z","timestamp":1779420420000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786335.3813203"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,26]]},"references-count":30,"alternative-id":["10.1145\/3786335.3813203","10.1145\/3786335"],"URL":"https:\/\/doi.org\/10.1145\/3786335.3813203","relation":{},"subject":[],"published":{"date-parts":[[2026,5,26]]},"assertion":[{"value":"2026-05-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}