{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:08:25Z","timestamp":1788894505696,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370341","type":"print"},{"value":"9783032370358","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37035-8_28","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:52:15Z","timestamp":1788893535000},"page":"507-524","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["WebRetriever: A Large-Scale Comprehensive Benchmark for\u00a0Efficient Web Agent Evaluation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1085-8735","authenticated-orcid":false,"given":"Wei","family":"Dong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7656-350X","authenticated-orcid":false,"given":"Tianyu","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7896-8412","authenticated-orcid":false,"given":"Zhe","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1474-3657","authenticated-orcid":false,"given":"Hanning","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0085-3527","authenticated-orcid":false,"given":"Anyang","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7141-7121","authenticated-orcid":false,"given":"Zhizhou","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0256-4979","authenticated-orcid":false,"given":"Yuyang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9907-6186","authenticated-orcid":false,"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4577-3002","authenticated-orcid":false,"given":"Minghui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6161-060X","authenticated-orcid":false,"given":"Ping","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0791-189X","authenticated-orcid":false,"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4044-5701","authenticated-orcid":false,"given":"Chenxu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"28_CR1","unstructured":"Abuelsaad, T., Akkil, D., Dey, P., Jagmohan, A., Vempaty, A., Kokku, R.: Agent-e: from autonomous web navigation to foundational design principles in agentic systems. arXiv preprint arXiv:2407.13032 (2024)"},{"key":"28_CR2","unstructured":"Anthropic: Introducing claude sonnet 4.5. Official Product Announcement (2025). https:\/\/www.anthropic.com\/news\/claude-sonnet-4-5"},{"key":"28_CR3","unstructured":"Bai, S., et al.: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"28_CR4","doi-asserted-by":"publisher","first-page":"78142","DOI":"10.52202\/075280-3414","volume":"36","author":"Y Bai","year":"2023","unstructured":"Bai, Y., et al.: Benchmarking foundation models with language-model-as-an-examiner. Adv. Neural. Inf. Process. Syst. 36, 78142\u201378167 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR5","doi-asserted-by":"publisher","first-page":"5996","DOI":"10.52202\/079017-0195","volume":"37","author":"L Boisvert","year":"2024","unstructured":"Boisvert, L., et al.: Workarena++: towards compositional planning and reasoning-based common knowledge work tasks. Adv. Neural. Inf. Process. Syst. 37, 5996\u20136051 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Q., Pitawela, D., Zhao, C., Zhou, G., Chen, H.T., Wu, Q.: Webvln: vision-and-language navigation on websites. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 1165\u20131173 (2024)","DOI":"10.1609\/aaai.v38i2.27878"},{"key":"28_CR7","unstructured":"Chen, S., Wiseman, S., Dhingra, B.: Chatshop: interactive information seeking with language agents. arXiv preprint arXiv:2404.09911 (2024)"},{"key":"28_CR8","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"28_CR9","doi-asserted-by":"publisher","first-page":"28091","DOI":"10.52202\/075280-1220","volume":"36","author":"X Deng","year":"2023","unstructured":"Deng, X., et al.: Mind2web: towards a generalist agent for the web. Adv. Neural. Inf. Process. Syst. 36, 28091\u201328114 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Deng, Y., Zhang, X., Zhang, W., Yuan, Y., Ng, S.K., Chua, T.S.: On the multi-turn instruction following for conversational web agents. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 8795\u20138812 (2024)","DOI":"10.18653\/v1\/2024.acl-long.477"},{"key":"28_CR11","unstructured":"Drouin, A., et al.: Workarena: how capable are web agents at solving common knowledge work tasks? arXiv preprint arXiv:2403.07718 (2024)"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Fan, Y., et al.: Videoagent: a memory-augmented multimodal agent for video understanding. In: European Conference on Computer Vision, pp. 75\u201392. Springer (2024)","DOI":"10.1007\/978-3-031-72670-5_5"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Fernandes, P., et al.: The devil is in the errors: leveraging large language models for fine-grained machine translation evaluation. arXiv preprint arXiv:2308.07286 (2023)","DOI":"10.18653\/v1\/2023.wmt-1.100"},{"key":"28_CR14","unstructured":"Fu, T., et al.: Mano technical report. arXiv preprint arXiv:2509.17336 (2025)"},{"key":"28_CR15","unstructured":"Furuta, H., Matsuo, Y., Faust, A., Gur, I.: Language model agents suffer from compositional generalization in web automation. In: NeurIPS 2023 Foundation Models for Decision Making Workshop (2023)"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Garg, D., et al.: Real: benchmarking autonomous agents on deterministic simulations of real websites. arXiv preprint arXiv:2504.11543 (2025)","DOI":"10.52202\/085713-4536"},{"key":"28_CR17","unstructured":"Guo, D., et al.: Seed1. 5-vl technical report. arXiv preprint arXiv:2505.07062 (2025)"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"He, H., et al.: Webvoyager: building an end-to-end web agent with large multimodal models. arXiv preprint arXiv:2401.13919 (2024)","DOI":"10.18653\/v1\/2024.acl-long.371"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Hong, W., et al.: Cogagent: a visual language model for GUI agents. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14281\u201314290 (2024)","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"28_CR20","unstructured":"Hurst, A., et al.: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Kapoor, R., et al.: Omniact: a dataset and benchmark for enabling multimodal generalist autonomous agents for desktop and web. In: European Conference on Computer Vision, pp. 161\u2013178. Springer (2024)","DOI":"10.1007\/978-3-031-73113-6_10"},{"key":"28_CR22","unstructured":"Kara, S., Faisal, F., Nath, S.: Waber: evaluating reliability and efficiency of web agents with existing benchmarks. In: ICLR 2025 Workshop on Foundation Models in the Wild (2025)"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Koh, J.Y., et al.: Visualwebarena: evaluating multimodal agents on realistic visual web tasks. arXiv preprint arXiv:2401.13649 (2024)","DOI":"10.18653\/v1\/2024.acl-long.50"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Lai, H., et al.: Autowebglm: a large language model-based web navigating agent. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 5295\u20135306 (2024)","DOI":"10.1145\/3637528.3671620"},{"key":"28_CR25","unstructured":"Levy, I., Wiesel, B., Marreed, S., Oved, A., Yaeli, A., Shlomov, S.: St-webagentbench: a benchmark for evaluating safety and trustworthiness in web agents. arXiv preprint arXiv:2410.06703 (2024)"},{"key":"28_CR26","unstructured":"Li, X., et al.: Alpacaeval: an automatic evaluator of instruction-following models (2023)"},{"key":"28_CR27","unstructured":"Liu, E.Z., Guu, K., Pasupat, P., Shi, T., Liang, P.: Reinforcement learning on web interfaces using workflow-guided exploration. arXiv preprint arXiv:1802.08802 (2018)"},{"key":"28_CR28","unstructured":"Liu, J., et al.: Visualwebbench: how far have multimodal LLMs evolved in web page understanding and grounding? arXiv preprint arXiv:2404.05955 (2024)"},{"key":"28_CR29","unstructured":"Liu, X., et al.: Agentbench: evaluating LLMs as agents. arXiv preprint arXiv:2308.03688 (2023)"},{"key":"28_CR30","unstructured":"Liu, X., et al.: Visualagentbench: towards large multimodal models as visual foundation agents. arXiv preprint arXiv:2408.06327 (2024)"},{"key":"28_CR31","unstructured":"L\u00f9, X.H., Kasner, Z., Reddy, S.: Weblinx: real-world website navigation with multi-turn dialogue (2024)"},{"key":"28_CR32","unstructured":"OpenAI: o4-mini: Fast and cost-efficient reasoning model. Official Product Announcement (2025). https:\/\/openai.com\/index\/introducing-o3-and-o4-mini\/"},{"key":"28_CR33","unstructured":"Pan, J., Zhang, Y., Tomlin, N., Zhou, Y., Levine, S., Suhr, A.: Autonomous evaluation and refinement of digital agents. arXiv preprint arXiv:2404.06474 (2024)"},{"key":"28_CR34","unstructured":"Pan, Y., et al.: Webcanvas: benchmarking web agents in online environments. arXiv preprint arXiv:2406.12373 (2024)"},{"key":"28_CR35","unstructured":"Qin, Y., et al.: UI-tars: pioneering automated GUI interaction with native agents. arXiv preprint arXiv:2501.12326 (2025)"},{"key":"28_CR36","unstructured":"Shi, T., Karpathy, A., Fan, L., Hernandez, J., Liang, P.: World of bits: an open-domain platform for web-based agents. In: International Conference on Machine Learning, pp. 3135\u20133144. PMLR (2017)"},{"key":"28_CR37","unstructured":"Song, Y., Thai, K., Pham, C.M., Chang, Y., Nadaf, M., Iyyer, M.: Bearcubs: a benchmark for computer-using web agents. arXiv preprint arXiv:2503.07919 (2025)"},{"key":"28_CR38","doi-asserted-by":"crossref","unstructured":"Tian, S., Zhang, Z., Chen, L.Y., Liu, Z.: Mmina: benchmarking multihop multimodal internet agents. In: Findings of the Association for Computational Linguistics: ACL 2025, pp. 13682\u201313697 (2025)","DOI":"10.18653\/v1\/2025.findings-acl.703"},{"key":"28_CR39","doi-asserted-by":"publisher","first-page":"115963","DOI":"10.52202\/079017-3682","volume":"37","author":"M Wornow","year":"2024","unstructured":"Wornow, M., et al.: Wonderbread: a benchmark for evaluating multimodal foundation models on business process management tasks. Adv. Neural. Inf. Process. Syst. 37, 115963\u2013116021 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR40","unstructured":"Xu, Y., et al.: Agenttrek: agent trajectory synthesis via guiding replay with web tutorials. arXiv preprint arXiv:2412.09605 (2024)"},{"key":"28_CR41","unstructured":"Xue, T., et al.: An illusion of progress? Assessing the current state of web agents. In: Second Conference on Language Modeling (2025). https:\/\/openreview.net\/forum?id=6jZi4HSs6o"},{"key":"28_CR42","doi-asserted-by":"crossref","unstructured":"Yao, S., Chen, H., Yang, J., Narasimhan, K.: Webshop: towards scalable real-world web interaction with grounded language agents. arXiv preprint (2022)","DOI":"10.52202\/068431-1508"},{"key":"28_CR43","doi-asserted-by":"crossref","unstructured":"Yoran, O., Amouyal, S.J., Malaviya, C., Bogin, B., Press, O., Berant, J.: Assistantbench: can web agents solve realistic and time-consuming tasks? arXiv preprint arXiv:2407.15711 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.505"},{"key":"28_CR44","unstructured":"Zheng, B., Gou, B., Kil, J., Sun, H., Su, Y.: GPT-4v (ision) is a generalist web agent, if grounded. arXiv preprint arXiv:2401.01614 (2024)"},{"key":"28_CR45","doi-asserted-by":"publisher","first-page":"46595","DOI":"10.52202\/075280-2020","volume":"36","author":"L Zheng","year":"2023","unstructured":"Zheng, L., et al.: Judging LLM-as-a-judge with MT-bench and chatbot arena. Adv. Neural. Inf. Process. Syst. 36, 46595\u201346623 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR46","unstructured":"Zhou, S., et al.: Webarena: a realistic web environment for building autonomous agents. In: ICLR (2024)"},{"key":"28_CR47","unstructured":"Zunic, G.: Browser use = state of the art web agent. Blog Technical Report (2024). https:\/\/browser-use.com\/posts\/sota-technical-report"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37035-8_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:52:22Z","timestamp":1788893542000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37035-8_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370341","9783032370358"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37035-8_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}