{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:10:31Z","timestamp":1789038631047,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373922","type":"print"},{"value":"9783032373939","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\/978-3-032-37393-9_17","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:37:19Z","timestamp":1789036639000},"page":"275-292","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MolmoWeb: Open Visual Web Agent and\u00a0Open Data for\u00a0the\u00a0Open Web"],"prefix":"10.1007","author":[{"given":"Tanmay","family":"Gupta","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Piper","family":"Wolters","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixian","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Sushko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rock Yuren","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taira","family":"Anderson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongzheng","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harsh","family":"Trivedi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Winson","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ranjay","family":"Krishna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"17_CR1","unstructured":"Andreux, M., et al.: Surfer-H meets Holo1: cost-efficient web agent powered by open weights. ArXiv abs\/2506.02865 (2025). https:\/\/api.semanticscholar.org\/CorpusID:279119644"},{"key":"17_CR2","unstructured":"Awadallah, A., et al.: Fara-7B: an efficient agentic model for computer use (2025). arXiv:2511.19663"},{"key":"17_CR3","unstructured":"de\u00a0Chezelles, T.L.S., et al.: The BrowserGym ecosystem for web agent research. ArXiv abs\/2412.05467 (2024). https:\/\/api.semanticscholar.org\/CorpusID:274598279"},{"key":"17_CR4","unstructured":"Clark, C., et al.: Molmo2: open weights and data for vision-language models with video understanding and grounding (2026). https:\/\/arxiv.org\/abs\/2601.10611"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Deng, X., et al.: Mind2Web: towards a generalist agent for the web. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","DOI":"10.52202\/075280-1220"},{"key":"17_CR6","unstructured":"Fourney, A., et al.: Magentic-one: a generalist multi-agent system for solving complex tasks (2024). https:\/\/arxiv.org\/abs\/2411.04468"},{"key":"17_CR7","unstructured":"Google: Computer use | Gemini API | Google AI for developers. Documentation. https:\/\/ai.google.dev\/gemini-api\/docs\/computer-use. Accessed 05 Mar 2026"},{"key":"17_CR8","unstructured":"Google: Computer use | Gemini API documentation (2026). https:\/\/ai.google.dev\/gemini-api\/docs\/computer-use. Accessed 04 Mar 2026"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Gundersen, O.E., Kjensmo, S.: State of the art: reproducibility in artificial intelligence. In: AAAI Conference on Artificial Intelligence (AAAI) (2018). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/11503","DOI":"10.1609\/aaai.v32i1.11503"},{"key":"17_CR10","unstructured":"Gur, I., et al.: A real-world WebAgent with planning, long context understanding, and program synthesis. arXiv preprint: arXiv:2307.12856 (2023)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"He, H., et al.: WebVoyager: building an end-to-end web agent with large multimodal models. In: ACL (2024)","DOI":"10.18653\/v1\/2024.acl-long.371"},{"key":"17_CR12","unstructured":"Hong, W., et al.: GLM-4.5 V and GLM-4.1 V-thinking: towards versatile multimodal reasoning with scalable reinforcement learning. arXiv preprint: arXiv:2507.01006 (2025)"},{"key":"17_CR13","unstructured":"International Telecommunication Union (ITU): Facts and figures 2024: Internet use. Web page (2024). https:\/\/www.itu.int\/itu-d\/reports\/statistics\/2024\/11\/10\/ff24-internet-use\/. Accessed 05 Mar 2026"},{"key":"17_CR14","unstructured":"Koh, J.Y., et al.: VisualWebArena: evaluating multimodal agents on realistic visual web tasks. ArXiv abs\/2401.13649 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267199749"},{"key":"17_CR15","unstructured":"Koh, J.Y., McAleer, S., Fried, D., Salakhutdinov, R.: Tree search for language model agents. arXiv preprint: arXiv:2407.01476 (2024)"},{"key":"17_CR16","unstructured":"Lai, H., et al.: AutoWebGLM: bootstrap and reinforce a large language model-based web navigating agent (2024). https:\/\/arxiv.org\/abs\/2404.03648"},{"key":"17_CR17","unstructured":"Liu, E.Z., Guu, K., Pasupat, P., Shi, T.T., Liang, P.: Reinforcement learning on web interfaces using workflow-guided exploration. In: International Conference on Learning Representations (ICLR) (2018). https:\/\/arxiv.org\/pdf\/1802.08802"},{"key":"17_CR18","unstructured":"Lu, Y., Yang, J., Shen, Y., Awadallah, A.: OmniParser for pure vision based GUI agent. ArXiv abs\/2408.00203 (2024). https:\/\/api.semanticscholar.org\/CorpusID:271601072"},{"key":"17_CR19","unstructured":"Lyu, Y., Zhang, X., Yan, L., de\u00a0Rijke, M., Ren, Z., Chen, X.: DeepShop: a benchmark for deep research shopping agents. ArXiv abs\/2506.02839 (2025). https:\/\/api.semanticscholar.org\/CorpusID:279118560"},{"key":"17_CR20","unstructured":"Nakano, R., et al.: WebGPT: browser-assisted question-answering with human feedback. arXiv preprint: arXiv:2112.09332 (2021)"},{"key":"17_CR21","unstructured":"National Institute of Standards and Technology (NIST): Artificial intelligence risk management framework (AI RMF 1.0). NIST Special Publication (2023). https:\/\/nvlpubs.nist.gov\/nistpubs\/ai\/nist.ai.100-1.pdf. Accessed 05 Mar 2026"},{"key":"17_CR22","unstructured":"OECD: Briefing note: Digital skills and digital inclusion. PDF (2023). https:\/\/www.oecd.org\/content\/dam\/oecd\/en\/about\/projects\/cfe\/oecd-city-network-on-jobs-and-skills\/Briefing-note-Digital-skills-and-digital-inclusion.pdf. Accessed 05 Mar 2026"},{"key":"17_CR23","unstructured":"OpenAI: Computer use | OpenAI API. Documentation. https:\/\/developers.openai.com\/api\/docs\/guides\/tools-computer-use\/. Accessed 05 Mar 2026"},{"key":"17_CR24","unstructured":"OpenAI: Computer use | OpenAI API documentation (2025). https:\/\/developers.openai.com\/api\/docs\/guides\/tools-computer-use\/. Accessed 04 Mar 2026"},{"key":"17_CR25","unstructured":"OpenAI: OpenAI for developers in 2025. Blog post (2025). https:\/\/developers.openai.com\/blog\/openai-for-developers-2025\/. Accessed 05 Mar 2026"},{"key":"17_CR26","unstructured":"Pan, Y., et\u00a0al.: WebCanvas: benchmarking web agents in online environments. arXiv preprint: arXiv:2406.12373 (2024)"},{"key":"17_CR27","unstructured":"Pineau, J., et al.: Improving reproducibility in machine learning research (a report from the NeurIPS 2019 reproducibility program). J. Mach. Learn. Res. 22(164) (2021). https:\/\/jmlr.org\/papers\/v22\/20-303.html"},{"key":"17_CR28","unstructured":"Qian, R., et al.: UGround: towards unified visual grounding with unrolled transformers. ArXiv abs\/2510.03853 (2025). https:\/\/api.semanticscholar.org\/CorpusID:281843677"},{"key":"17_CR29","unstructured":"Qin, Y., et al.: UI-TARS: pioneering automated GUI interaction with native agents. ArXiv abs\/2501.12326 (2025). https:\/\/api.semanticscholar.org\/CorpusID:275788034"},{"key":"17_CR30","unstructured":"Seed, B.: UI-TARS-1.5 (2025). https:\/\/seed-tars.com\/1.5"},{"key":"17_CR31","unstructured":"Shi, T.T., Karpathy, A., Fan, L., Hernandez, J., Liang, P., et\u00a0al.: World of bits: an open-domain platform for web-based agents. In: Proceedings of the 34th International Conference on Machine Learning (ICML) (2017). https:\/\/proceedings.mlr.press\/v70\/shi17a\/shi17a.pdf"},{"key":"17_CR32","unstructured":"Shi, T., Karpathy, A., Fan, L.J., Hern\u00e1ndez, J.Z., Liang, P.: World of bits: an open-domain platform for web-based agents. In: International Conference on Machine Learning (2017). https:\/\/api.semanticscholar.org\/CorpusID:34953552"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Song, Y., Xu, F.F., Zhou, S., Neubig, G.: Beyond browsing: API-based web agents. In: Annual Meeting of the Association for Computational Linguistics (2024). https:\/\/api.semanticscholar.org\/CorpusID:273507298","DOI":"10.18653\/v1\/2025.findings-acl.577"},{"key":"17_CR34","unstructured":"Team, T.Y.: Introducing navigator (2025). https:\/\/yutori.com\/blog\/introducing-navigator. yutori Blog"},{"key":"17_CR35","unstructured":"Trivedi, H., et al.: AppWorld: a controllable world of apps and people for benchmarking interactive coding agents. ArXiv abs\/2407.18901 (2024). https:\/\/api.semanticscholar.org\/CorpusID:271516633"},{"key":"17_CR36","unstructured":"W3C Web Accessibility Initiative (WAI): Diverse abilities and barriers. Web page (2024). https:\/\/www.w3.org\/WAI\/people-use-web\/abilities-barriers\/. Accessed 05 Mar 2026"},{"key":"17_CR37","unstructured":"Wang, H., et\u00a0al.: UI-TARS-2 technical report: advancing GUI agent with multi-turn reinforcement learning. arXiv preprint: arXiv:2509.02544 (2025)"},{"key":"17_CR38","unstructured":"Wang, P., et\u00a0al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint: arXiv:2409.12191 (2024)"},{"key":"17_CR39","unstructured":"Wang, X., et al.: OpenCUA: open foundations for computer-use agents. ArXiv abs\/2508.09123 (2025). https:\/\/api.semanticscholar.org\/CorpusID:280635573"},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Weidinger, L., Uesato, J., Rauh, M., Griffin, C., Mellor, J., et\u00a0al.: Taxonomy of risks posed by language models. In: Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency (FAccT) (2022), https:\/\/facctconference.org\/static\/pdfs_2022\/facct22-3533088.pdf","DOI":"10.1145\/3531146.3533088"},{"key":"17_CR41","unstructured":"World Health Organization (WHO): Disability and health. Web page (2023). https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/disability-and-health. Accessed 05 Mar 2026"},{"key":"17_CR42","unstructured":"Wu, Y., et al.: AutoWebWorld: synthesizing infinite verifiable web environments via finite state machines (2026). https:\/\/arxiv.org\/abs\/2602.14296"},{"key":"17_CR43","unstructured":"Xue, T., et al.: An illusion of progress? Assessing the current state of web agents. ArXiv abs\/2504.01382 (2025). https:\/\/api.semanticscholar.org\/CorpusID:277502135"},{"key":"17_CR44","unstructured":"Yang, J., Zhang, H., Li, F., Zou, X., Li, C., Gao, J.: Set-of-mark prompting unleashes extraordinary visual grounding in GPT-4V. arXiv preprint: arXiv:2310.11441 (2023)"},{"key":"17_CR45","doi-asserted-by":"crossref","unstructured":"You, K., et al.: Ferret-UI: grounded mobile UI understanding with multimodal LLMs. In: European Conference on Computer Vision (2024). https:\/\/api.semanticscholar.org\/CorpusID:269005503","DOI":"10.1007\/978-3-031-73039-9_14"},{"key":"17_CR46","unstructured":"Zhou, S., et al.: WebArena: a realistic web environment for building autonomous agents. ArXiv abs\/2307.13854 (2023). https:\/\/api.semanticscholar.org\/CorpusID:260164780"}],"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\/978-3-032-37393-9_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:37:37Z","timestamp":1789036657000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37393-9_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373922","9783032373939"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37393-9_17","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":"11 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"}}]}}