{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:09:00Z","timestamp":1784138940039,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"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":[[2026,7,20]]},"DOI":"10.1145\/3805712.3808592","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"3342-3348","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["WebMall - A Multi-Shop Benchmark for Evaluating Web Agents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3174-2616","authenticated-orcid":false,"given":"Ralph","family":"Peeters","sequence":"first","affiliation":[{"name":"Data and Web Science Group, University of Mannheim, Mannheim, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6946-7057","authenticated-orcid":false,"given":"Aaron","family":"Steiner","sequence":"additional","affiliation":[{"name":"Data and Web Science Group, University of Mannheim, Mannheim, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4751-4607","authenticated-orcid":false,"given":"Luca","family":"Schwarz","sequence":"additional","affiliation":[{"name":"Data and Web Science Group, University of Mannheim, Mannheim, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0606-4115","authenticated-orcid":false,"given":"Julian Yuya","family":"Caspary","sequence":"additional","affiliation":[{"name":"Data and Web Science Group, University of Mannheim, Mannheim, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2367-0237","authenticated-orcid":false,"given":"Christian","family":"Bizer","sequence":"additional","affiliation":[{"name":"Data and Web Science Group, University of Mannheim, Mannheim, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Thibault Le Sellier de Chezelles Maxime Gasse Alexandre Lacoste Massimo Caccia Alexandre Drouin et al. 2025. The BrowserGym Ecosystem for Web Agent Research. Transactions on Machine Learning Research (2025)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1220"},{"key":"e_1_3_2_1_3_1","unstructured":"Mohamed Amine Ferrag Norbert Tihanyi and Merouane Debbah. 2025. From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review. arXiv:2504.19678"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 39th Annual Conference on Neural Information Processing Systems.","author":"Garg Divyansh","year":"2026","unstructured":"Divyansh Garg, Diego Caples, Andis Draguns, Nikil Ravi, Pranav Putta, et al., 2026. REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites. In Proceedings of the 39th Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3774904.3792724"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.50"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2026.eacl-industry.62"},{"key":"e_1_3_2_1_8_1","first-page":"52989","volume-title":"Proceedings of the International Conference on Learning Representations","volume":"2024","author":"Liu Xiao","year":"2024","unstructured":"Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, et al., 2024. AgentBench: Evaluating LLMs as Agents. In Proceedings of the International Conference on Learning Representations, Vol. 2024. 52989-53046."},{"key":"e_1_3_2_1_9_1","unstructured":"Yougang Lyu Xiaoyu Zhang Lingyong Yan Maarten de Rijke Zhaochun Ren et al. 2025. DeepShop: A Benchmark for Deep Research Shopping Agents. arXiv:2506.02839"},{"key":"e_1_3_2_1_10_1","unstructured":"Atsuyuki Miyai Zaiying Zhao Kazuki Egashira Atsuki Sato Tatsumi Sunada et al. 2025. WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks. arXiv:2506.01952"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736555"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the ACM Web Conference","author":"Steiner Aaron","year":"2026","unstructured":"Aaron Steiner, Ralph Peeters, and Christian Bizer. 2026. MCP vs RAG vs NLWeb vs HTML: A Comparison of the Effectiveness and Efficiency of Different Agent Interfaces to the Web. In Proceedings of the ACM Web Conference 2026. 8493\u20138496."},{"key":"e_1_3_2_1_13_1","unstructured":"Huaixiao Tou Ying Zeng Yuemeng Li Cong Ma Muzhi Li et al. 2026. ShoppingComp: Are LLMs Really Ready for Your Shopping Cart ? arXiv:2511.22978"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i39.40640"},{"key":"e_1_3_2_1_15_1","volume-title":"Frontiers of Computer Science","volume":"18","author":"Wang Lei","year":"2024","unstructured":"Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, et al., 2024. A Survey on Large Language Model based Autonomous Agents. Frontiers of Computer Science, Vol. 18, 6 (2024)."},{"key":"e_1_3_2_1_16_1","unstructured":"Jason Wei Zhiqing Sun Spencer Papay Scott McKinney Jeffrey Han et al. 2025. BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents. arXiv:2504.12516"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 2nd Conference on Language Modeling.","author":"Xue Tianci","year":"2025","unstructured":"Tianci Xue, Weijian Qi, Tianneng Shi, Chan Hee Song, Boyu Gou, et al., 2025. An Illusion of Progress? Assessing the Current State of Web Agents. In Proceedings of the 2nd Conference on Language Modeling."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1508"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Xianren Zhang Shreyas Prasad Di Wang Qiuhai Zeng Suhang Wang et al. 2026. A Functionality-Grounded Benchmark for Evaluating Web Agents in E-commerce Domains. arXiv:2508.15832","DOI":"10.18653\/v1\/2026.acl-long.68"},{"key":"e_1_3_2_1_20_1","first-page":"15585","volume-title":"Proceedings of the International Conference on Learning Representations","volume":"2024","author":"Zhou Shuyan","year":"2024","unstructured":"Shuyan Zhou, Frank F Xu, Hao Zhu, Xuhui Zhou, Robert Lo, et al., 2024. WebArena: A Realistic Web Environment for Building Autonomous Agents. In Proceedings of the International Conference on Learning Representations, Vol. 2024. 15585-15606."}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:32:09Z","timestamp":1784136729000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3808592"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":20,"alternative-id":["10.1145\/3805712.3808592","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3808592","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}