{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T23:09:14Z","timestamp":1788995354770,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375766","type":"print"},{"value":"9783032375773","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\/978-3-032-37577-3_12","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T22:59:28Z","timestamp":1788994768000},"page":"210-227","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning from\u00a0Failure: Inference-Time Self-improvement for\u00a0Computer-Use Agents"],"prefix":"10.1007","author":[{"given":"Xueqiao","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ludwig","family":"Schmidt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Serena","family":"Yeung-Levy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"12_CR1","unstructured":"Agashe, S., Han, J., Gan, S., Yang, J., Li, A., Wang, X.E.: Agent S: an open agentic framework that uses computers like a human. arXiv preprint arXiv:2410.08164 (2024)"},{"key":"12_CR2","unstructured":"Agashe, S., Wong, K., Tu, V., Yang, J., Li, A., Wang, X.E.: Agent S2: aacompositional generalist-specialist framework for computer use agents. arXiv preprint arXiv:2504.00906 (2025)"},{"key":"12_CR3","unstructured":"Anthropic: Claude 3.7 sonnet and claude code. Technical report, Anthropic (2025). https:\/\/www.anthropic.com\/news\/claude-3-7-sonnet. System Card"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Deng, X., et al.: Mind2web: towards a generalist agent for the web (2023). https:\/\/arxiv.org\/abs\/2306.06070","DOI":"10.52202\/075280-1220"},{"key":"12_CR5","doi-asserted-by":"publisher","unstructured":"Feizi, A.: Grounding computer use agents on human demonstrations. arXiv:2511.07332 (2025). https:\/\/doi.org\/10.48550\/arXiv.2511.07332","DOI":"10.48550\/arXiv.2511.07332"},{"key":"12_CR6","unstructured":"He, H., et al.: Webvoyager: building an end-to-end web agent with large multimodal models (2024). https:\/\/arxiv.org\/abs\/2401.13919"},{"key":"12_CR7","doi-asserted-by":"publisher","unstructured":"He, Y.: Efficient agent training for computer use. arXiv preprint arXiv:2505.13909 (2025). https:\/\/doi.org\/10.48550\/arXiv.2505.13909","DOI":"10.48550\/arXiv.2505.13909"},{"key":"12_CR8","unstructured":"Hu, X.: OS agents: A survey on MLLM-based agents for general computing devices use. arXiv preprint arXiv:2508.04482 (2025). https:\/\/doi.org\/10.48550\/arXiv.2508.04482. Accepted by ACL 2025 (Oral)"},{"key":"12_CR9","doi-asserted-by":"publisher","unstructured":"Hu, X., et al.: OS agents: a survey on MLLM-based agents for computer, phone and browser use. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 7436\u20137465. Association for Computational Linguistics, Vienna (2025). https:\/\/doi.org\/10.18653\/v1\/2025.acl-long.369, https:\/\/aclanthology.org\/2025.acl-long.369","DOI":"10.18653\/v1\/2025.acl-long.369"},{"key":"12_CR10","unstructured":"Huo, Y.: Sea: Self-evolution agent with step-wise reward for computer use. arXiv (2025). arXiv:2508.04037 [cs.AI]"},{"key":"12_CR11","doi-asserted-by":"publisher","unstructured":"Juan, X.: A survey of self-evolving agents: on path to artificial super intelligence. arXiv:2507.21046 (2025). https:\/\/doi.org\/10.48550\/arXiv.2507.21046","DOI":"10.48550\/arXiv.2507.21046"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Kapoor, R., et al.: OmniAct: a dataset and benchmark for enabling multimodal generalist autonomous agents for desktop and web (2024). https:\/\/arxiv.org\/abs\/2402.17553","DOI":"10.1007\/978-3-031-73113-6_10"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: Screenspot-pro: GUI grounding for professional high-resolution computer use (2025). https:\/\/arxiv.org\/abs\/2504.07981","DOI":"10.1145\/3746027.3755688"},{"key":"12_CR14","unstructured":"Li, W., et al.: On the effects of data scale on UI control agents (2024). https:\/\/arxiv.org\/abs\/2406.03679"},{"key":"12_CR15","unstructured":"Liu, Y., et al.: Infigui-R1: advancing multimodal GUI agents from reactive actors to deliberative reasoners. arXiv preprint arXiv:2504.14239 (2025)"},{"key":"12_CR16","unstructured":"OpenAI: OpenAI o3 and o4-mini system card. Technical report, OpenAI (2025). https:\/\/cdn.openai.com\/pdf\/2221c875-02dc-4789-800b-e7758f3722c1\/o3-and-o4-mini-system-card.pdf. System Card"},{"key":"12_CR17","unstructured":"Qin, Y., et al.: UI-tars: pioneering automated GUI interaction with native agents (2025). https:\/\/arxiv.org\/abs\/2501.12326"},{"key":"12_CR18","unstructured":"Qin, Y., et\u00a0al.: UI-tars: pioneering automated GUI interaction with native agents. arXiv preprint arXiv:2501.12326 (2025)"},{"key":"12_CR19","doi-asserted-by":"publisher","unstructured":"Song, L.: CoAct-1: computer-using agents with coding as actions. arXiv:2508.03923 (2025). https:\/\/doi.org\/10.48550\/arXiv.2508.03923","DOI":"10.48550\/arXiv.2508.03923"},{"key":"12_CR20","unstructured":"Sun, Z.: SEAgent: self-evolving computer use agent with autonomous learning from experience. arXiv:2508.04700 [cs.AI] (2025)"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Wang, B., Li, G., Zhou, X., Chen, Z., Grossman, T., Li, Y.: Screen2Words: automatic mobile UI summarization with multimodal learning (2021). https:\/\/arxiv.org\/abs\/2108.03353","DOI":"10.1145\/3472749.3474765"},{"key":"12_CR22","unstructured":"Wang, X., et al.: OpenCUA: open foundations for computer-use agents (2025). https:\/\/arxiv.org\/abs\/2508.09123"},{"key":"12_CR23","doi-asserted-by":"publisher","unstructured":"Wu, J., Zhang, X., Nichols, J., Bigham, J.P.: Screen parsing: towards reverse engineering of UI models from screenshots. In: The 34th Annual ACM Symposium on User Interface Software and Technology, UIST 2021, pp. 470\u2013483. ACM (2021). https:\/\/doi.org\/10.1145\/3472749.3474763","DOI":"10.1145\/3472749.3474763"},{"key":"12_CR24","doi-asserted-by":"publisher","unstructured":"Wu, Z.: See, think, act: teaching multimodal agents to effectively interact with GUI by identifying toggles (2025). https:\/\/doi.org\/10.48550\/arXiv.2509.13615, https:\/\/arxiv.org\/abs\/2509.13615","DOI":"10.48550\/arXiv.2509.13615"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Xie, T., et\u00a0al.: Scaling computer-use grounding via user interface decomposition and synthesis. arXiv preprint arXiv:2505.13227 (2025)","DOI":"10.52202\/085713-0817"},{"key":"12_CR26","doi-asserted-by":"publisher","first-page":"52040","DOI":"10.52202\/079017-1650","volume":"37","author":"T Xie","year":"2024","unstructured":"Xie, T., et al.: OSWorld: Benchmarking multimodal agents for open-ended tasks in real computer environments. Adv. Neural. Inf. Process. Syst. 37, 52040\u201352094 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Xie, T., et al.: OSWorld: benchmarking multimodal agents for open-ended tasks in real computer environments (2024). https:\/\/arxiv.org\/abs\/2404.07972","DOI":"10.52202\/079017-1650"},{"key":"12_CR28","unstructured":"Xu, Y., et al.: Aguvis: unified pure vision agents for autonomous GUI interaction. arXiv preprint arXiv:2412.04454 (2024)"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: Aria-UI: visual grounding for GUI instructions. arXiv preprint arXiv:2412.16256 (2024)","DOI":"10.18653\/v1\/2025.findings-acl.1152"},{"key":"12_CR30","doi-asserted-by":"publisher","unstructured":"Yao, H.: A survey on agentic multimodal large language models. arXiv:2510.10991 (2025). https:\/\/doi.org\/10.48550\/arXiv.2510.10991","DOI":"10.48550\/arXiv.2510.10991"},{"key":"12_CR31","unstructured":"Ye, J., et al.: Mobile-agent-v3: fundamental agents for GUI automation (2025). https:\/\/arxiv.org\/abs\/2508.15144"},{"key":"12_CR32","doi-asserted-by":"publisher","unstructured":"Yuan, K.: Surfer 2: the next generation of cross-platform computer use agents. arXiv:2510.19949 (2025). https:\/\/doi.org\/10.48550\/arXiv.2510.19949","DOI":"10.48550\/arXiv.2510.19949"},{"key":"12_CR33","doi-asserted-by":"publisher","unstructured":"Yuan, X.: Enhancing visual grounding for GUI agents via self-evolutionary reinforcement learning. arXiv:2505.12370 [cs.AI] (2025). https:\/\/doi.org\/10.48550\/arXiv.2505.12370","DOI":"10.48550\/arXiv.2505.12370"},{"key":"12_CR34","doi-asserted-by":"publisher","unstructured":"Zhang, C.: Large language model-brained gui agents: a survey. arXiv preprint arXiv:2411.18279 (2025). https:\/\/doi.org\/10.48550\/arXiv.2411.18279","DOI":"10.48550\/arXiv.2411.18279"},{"key":"12_CR35","unstructured":"Zheng, B., Gou, B., Kil, J., Sun, H., Su, Y.: GPT-4v(ision) is a generalist web agent, if grounded (2024). https:\/\/arxiv.org\/abs\/2401.01614"},{"key":"12_CR36","doi-asserted-by":"publisher","unstructured":"Zhou, A.: UI-genie: a self-improving approach for iteratively boosting MLLM-based mobile GUI agents. arXiv (2025). https:\/\/doi.org\/10.48550\/arXiv.2505.21496, https:\/\/arxiv.org\/abs\/2505.21496. Version 1","DOI":"10.48550\/arXiv.2505.21496"},{"key":"12_CR37","unstructured":"Zhou, S., et al.: Webarena: a realistic web environment for building autonomous agents (2024). https:\/\/arxiv.org\/abs\/2307.13854"}],"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\/978-3-032-37577-3_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T22:59:35Z","timestamp":1788994775000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37577-3_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375766","9783032375773"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37577-3_12","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":"10 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"}}]}}