Elamur Research⌕
☰
home / papers / 2026 / WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent

WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent

Paper · 2026 · Lingfeng Zhang, Yongan Sun, Jinpeng Hu et al.

Summary

LLM-driven web agents often fail on long, interactive tasks. A plan fixed in advance can break when a page turns out differently than expected, while purely step-by-step planning can get stuck on local details. Over many steps, small hallucinated actions, such as clicking elements that do not exist, also add up. WebUncertainty is an agent framework that addresses both problems by estimating uncertainty at two levels.

At the planning level, an analysis agent scores how uncertain the task currently is. A planning agent then chooses one-shot explicit decomposition when uncertainty is low and reactive implicit planning when it is high. At the reasoning level, a Monte Carlo tree search expands candidate actions that come with self-reported confidence. The ConActU strategy turns these confidences into aleatoric (AU) and epistemic (EU) uncertainty, and an evaluation agent's scores are combined with them to guide the search.

On WebArena and WebVoyager, the system beats strong baselines and is faster than earlier search-based agents. This shows that modelling uncertainty explicitly makes web automation more reliable.

Key points

  • Results: with the Qwen-Max backbone, success rate (SR) reaches 63.6% on WebVoyager and 40.1% on WebArena. The strongest WebVoyager baseline, AgentOccam, scores 58.9%.
  • Ablation of planning modes: fixed modes show opposite preferences across benchmarks.
    • WebArena: explicit-only scores 39.2% and implicit-only 38.2%.
    • WebVoyager: implicit-only scores 58.1% and explicit-only 56.6%.
    • Adaptive switching beats both on each benchmark.
  • Ablation of ConActU: removing it, which leaves plain MCTS, gives the largest drop in SR: 9.3 on WebVoyager and 3.4 on WebArena.
  • Cost: average time per WebVoyager task is 351.4s, compared with 803.7s for WebPilot (over 56% less). SR also rises from 55.8% to 63.6%.
  • Settings and limitations:
    • The best thresholds are δ = 0.4 and τ = 6.
    • The agent is text-only and works on accessibility trees, so visually heavy sites remain difficult.
    • Code is available at github.com/windbd/WebUncertainty.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Hefei University of TechnologyHefei · China17 works · 1,702 citations

Also on the byline: China Electronics Technology Group Corporation.

 Fields, topics and concepts

📚 Shelves 3The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksInformation Systems · 1,730 works

🧭 Topics 1Research subjects and languages the work is about.Reasoning · 1,685 works

Cite

Cite as Lingfeng Zhang, Yongan Sun, Jinpeng Hu, Hui Ma, Ying Yang, Kuien Liu, Zenglin Shi and Meng Wang. 2026. WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.637

@inproceedings{zhang2026webuncertainty,
  title = {{WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent}},
  author = {Lingfeng Zhang, Yongan Sun, Jinpeng Hu, Hui Ma, Ying Yang, Kuien Liu, Zenglin Shi and Meng Wang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.637},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.637}
}

References

38 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Tamer Abuelsaad, Deepak Akkil, Prasenjit Dey, Ashish Jagmohan, Aditya Vempaty, and Ravi Kokku. 2024. Agent-E: from autonomous web navigation to foundational design principles in agentic systems. arXiv preprint. ArXiv:2407.13032 [cs]. — [arXiv:2407.13032](https://arxiv.org/abs/2407.13032) find
  2. Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang, Huan Sun, and Yu Su. 2023. MIND2WEB: towards a generalist agent for the web. In Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS ’23, pages 28091–28114, Red Hook, NY, USA. Curran…
  3. Yang Deng, An Zhang, Yankai Lin, Xu Chen, Ji-Rong Wen, and Tat-Seng Chua. 2024. Large language model powered agents in the web. In Companion Proceedings of the ACM Web Conference 2024, WWW ’24, pages 1242–1245, New York, NY, USA. Association for Computing Machinery. find
  4. Shangheng Du, Jiabao Zhao, Jinxin Shi, Zhentao Xie, Xin Jiang, Yanhong Bai, and Liang He. 2026. A survey on the optimization of large language model-based agents. ACM Computing Surveys, 58(9):1–37. find
  5. Lutfi Eren Erdogan, Nicholas Lee, Sehoon Kim, Suhong Moon, Hiroki Furuta, Gopala Anumanchipalli, Kurt Keutzer, and Amir Gholami. 2025. PLAN-AND-ACT: improving planning of agents for long-horizon tasks. In Proceedings of the 42nd International Conference on Machine Learning, volume 267 of ICML’25, pa… find
  6. Zeyu Gan, Yun Liao, and Yong Liu. 2025. Rethinking external slow-thinking: from snowball errors to probability of correct reasoning. In Proceedings of the 42nd International Conference on Machine Learning, pages 18170–18188. PMLR. ShortConferenceName: ICML. system. ACM Transactions on Information Sy… find
  7. Tanmay Gupta, Piper Wolters, Zixian Ma, Peter Sushko, Rock Yuren Pang, Diego Llanes, Yue Yang, Taira Anderson, Boyuan Zheng, Zhongzheng Ren, Harsh Trivedi, Taylor Blanton, Caleb Ouellette, Winson Han, Ali Farhadi, and Ranjay Krishna. 2026. Mol-moWeb: open visual web agent and open data for the open… find
  8. Tao Li, Gang Li, Zhiwei Deng, Bryan Wang, and Yang Li. 2023. A zero-shot language agent for computer control with structured reflection. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 11261–11274, Singapore. Association for Computational Linguistics. find
  9. 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, volume 2024, pages 52690–52717.
  10. Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Yong Dai, Hongming Zhang, Zhenzhong Lan, and Dong Yu. 2024. WebVoyager: building an end-to-end web agent with large multimodal models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), p…
  11. Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Hongming Zhang, Tianqing Fang, Zhenzhong Lan, and Dong Yu. 2025. OpenWebVoyager: building multimodal web agents via iterative real-world exploration, feedback and optimization. In Proceedings of the 63rd Annual Meeting of the Association for Computatio…
  12. Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, and 10 others. 2025. OS agents: a survey on MLLM-based agents for c…
  13. Tenghao Huang, Kinjal Basu, Ibrahim Abdelaziz, Pavan Kapanipathi, Jonathan May, and Muhao Chen. 2025. R2D2: remembering, replaying and dynamic decision making with a reflective agentic memory. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long… find
  14. Jing Yu Koh, Stephen McAleer, Daniel Fried, and Ruslan Salakhutdinov. 2024. Tree search for language model agents. arXiv preprint. Version Number: 4.
  15. Hanyu Lai, Xiao Liu, Hao Yu, Yifan Xu, Iat Long Iong, Shuntian Yao, Aohan Zeng, Zhengxiao Du, Yuxiao Dong, and Jie Tang. 2025. WebGLM: towards an efficient and reliable web-enhanced question-answering Evan Zheran Liu, Kelvin Guu, Panupong Pasupat, Tianlin Shi, and Percy Liang. 2018. Reinforcement le… find
  16. Haohao Luo, Jiayi Kuang, Wei Liu, Ying Shen, Jian Luan, and Yang Deng. 2025. Browsing like human: a multimodal web agent with experiential fast-and-slow thinking. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14232– 14251, V… find
  17. Huan Ma, Jingdong Chen, Joey Tianyi Zhou, Guangyu Wang, and Changqing Zhang. 2025. Estimating LLM uncertainty with evidence. arXiv preprint. ArXiv:2502.00290 [cs]. — [arXiv:2502.00290](https://arxiv.org/abs/2502.00290) find
  18. Dang Nguyen, Jian Chen, Yu Wang, Gang Wu, Namyong Park, Zhengmian Hu, Hanjia Lyu, Junda Wu, Ryan Aponte, Yu Xia, Xintong Li, Jing Shi, Hongjie Chen, Viet Dac Lai, Zhouhang Xie, Sungchul Kim, Ruiyi Zhang, Tong Yu, Mehrab Tanjim, and 11 others. 2025. GUI agents: a survey. In Findings of the Associatio… find
  19. Liangbo Ning, Ziran Liang, Zhuohang Jiang, Haohao Qu, Yujuan Ding, Wenqi Fan, Xiao-yong Wei, Shanru Lin, Hui Liu, Philip S. Yu, and Qing Li. 2025. A survey of WebAgents: towards next-generation AI agents for web automation with large foundation models. In Proceedings of the 31st ACM SIGKDD Conferenc… find
  20. Runliang Niu, Jindong Li, Shiqi Wang, Yali Fu, Xiyu Hu, Xueyuan Leng, He Kong, Yi Chang, and Qi Wang. 2024. ScreenAgent: a vision language model-driven computer control agent. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24, pages 6433– 6441. In… find
  21. Vardaan Pahuja, Yadong Lu, Corby Rosset, Boyu Gou, Arindam Mitra, Spencer Whitehead, Yu Su, and Ahmed Hassan Awadallah. 2025. Explorer: scaling exploration-driven web trajectory synthesis for multimodal web agents. In Findings of the Association for Computational Linguistics: ACL 2025, pages 6300–63… find
  22. Kevin Pu, Jim Yang, Angel Yuan, Minyi Ma, Rui Dong, Xinyu Wang, Yan Chen, and Tovi Grossman. 2023. DiLogics: creating web automation programs with diverse logics. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1–15, San Francisco CA USA. ACM. find
  23. Orit Shahnovsky and Rotem Dror. 2026. AI planning framework for LLM-based web agents. arXiv preprint. Version Number: 1. find
  24. Yueqi Song, Frank F. Xu, Shuyan Zhou, and Graham Neubig. 2025. Beyond browsing: API-based web agents. In Findings of the Association for Computational Linguistics: ACL 2025, pages 11066–11085, Vienna, Austria. Association for Computational Linguistics. find
  25. Tianxin Wei, Ting-Wei Li, Zhining Liu, Xuying Ning, Ze Yang, Jiaru Zou, Zhichen Zeng, Ruizhong Qiu, Xiao Lin, Dongqi Fu, Zihao Li, Mengting Ai, Duo Zhou, Wenxuan Bao, Yunzhe Li, Gaotang Li, Cheng Qian, Yu Wang, Xiangru Tang, and 10 others. 2026. Agentic reasoning for large language models. arXiv pre… find
  26. Jialong Wu, Wenbiao Yin, Yong Jiang, Zhenglin Wang, Zekun Xi, Runnan Fang, Linhai Zhang, Yulan He, Deyu Zhou, Pengjun Xie, and Fei Huang. 2025. Web-Walker: benchmarking LLMs in web traversal. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long P… find
  27. Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, Rui Zheng, Xiaoran Fan, Xiao Wang, Limao Xiong, Yuhao Zhou, Weiran Wang, Changhao Jiang, Yicheng Zou, Xiangyang Liu, and 9 others. 2025. The rise and potential of large language model…
  28. Zhiqiu Xia, Jinxuan Xu, Yuqian Zhang, and Hang Liu. 2025. A survey of uncertainty estimation methods on large language models. In Findings of the Association for Computational Linguistics: ACL 2025, pages 21381–21396, Vienna, Austria. Association for Computational Linguistics. find
  29. Ke Yang, Yao Liu, Sapana Chaudhary, Rasool Fakoor, Pratik Chaudhari, George Karypis, and Huzefa Rangwala. 2025a. AgentOccam: a simple yet strong baseline for LLM-based web agents. In The Thirteenth International Conference on Learning Representations. find
  30. Yingxuan Yang, Mulei Ma, Yuxuan Huang, Huacan Chai, Chenyu Gong, Haoran Geng, Yuanjian Zhou, Ying Wen, Meng Fang, Muhao Chen, Shangding Gu, Ming Jin, Costas Spanos, Yang Yang, Pieter Abbeel, Dawn Song, Weinan Zhang, and Jun Wang. 2025b. Agentic web: weaving the next web with AI agents. arXiv preprin… find
  31. Xiao Yu, Baolin Peng, Vineeth Vajipey, Hao Cheng, Michel Galley, Jianfeng Gao, and Zhou Yu. 2025. ExACT: teaching AI agents to explore with reflective-MCTS and exploratory learning. In International Conference on Learning Representations, volume 2025, pages 65157–65184. find
  32. Duzhen Zhang, Zhong-Zhi Li, Ming-Liang Zhang, Jiaxin Zhang, Zengyan Liu, Yuxuan Yao, Haotian Xu, Junhao Zheng, Xiuyi Chen, Yingying Zhang, Fei Yin, Jiahua Dong, Zhijiang Guo, Le Song, and Cheng-Lin Liu. 2026a. From system 1 to system 2: a survey of reasoning large language models. IEEE Transactions…
  33. Xuan Zhang, Yang Deng, Zifeng Ren, See-Kiong Ng, and Tat-Seng Chua. 2024. Ask-before-plan: proactive language agents for real-world planning. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10836–10863, Miami, Florida, USA. Association for Computational Linguistics. find
  34. Xuanwang Zhang, Yuteng Han, Jinnan Qi, Mulong Xie, Zhen Wu, and Xinyu Dai. 2026b. WebNavigator: global web navigation via interaction graph retrieval. arXiv preprint. Version Number: 1. find
  35. Yao Zhang, Zijian Ma, Yunpu Ma, Zhen Han, Yu Wu, and Volker Tresp. 2025. WebPilot: a versatile and autonomous multi-agent system for web task execution with strategic exploration. In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovativ… find
  36. Qiwei Zhao, Dong Li, Yanchi Liu, Wei Cheng, Yiyou Sun, Mika Oishi, Takao Osaki, Katsushi Matsuda, Huaxiu Yao, Chen Zhao, Haifeng Chen, and Xujiang Zhao. 2025. Uncertainty propagation on LLM agent. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: L… find
  37. Boyuan Zheng, Boyu Gou, Jihyung Kil, Huan Sun, and Yu Su. 2024. GPT-4V(ision) is a generalist web agent, if grounded. In Proceedings of the 41st International Conference on Machine Learning, volume 235 of Proceedings of Machine Learning Research, pages 61349–61385. PMLR.
  38. Shuyan Zhou, Frank F 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, volume 202…

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhang-2026-webuncertainty-dual-level-uncertainty-driven/