---
title: "Web Sitemap Knowledge Can Enhance Autonomous Browsing"
description: "To build these sitemaps cheaply, they introduce LightASM. 27 references. LLM-based web agents often fail on real websites."
authors: ["Yuyao Zhang", "Hongyu Lu", "Jiajie Jin", "Hongjin Qian", "Shiyu Li", "Zhao Yang", "Yutao Zhu", "Ji-Rong Wen", "Zhicheng Dou"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1465/"
doi: "10.18653/v1/2026.findings-acl.1465"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhang-2026-web-sitemap-knowledge-can-enhance/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-web-sitemap-knowledge-can-enhance/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/56/) / Web Sitemap Knowledge Can Enhance Autonomous Browsing

# Web Sitemap Knowledge Can Enhance Autonomous Browsing

**Authors:** [Yuyao Zhang](https://md.research.elamur.ai/free/en/authors/yuyao-zhang/), [Hongyu Lu](https://md.research.elamur.ai/free/en/authors/hongyu-lu/), [Jiajie Jin](https://md.research.elamur.ai/free/en/authors/jiajie-jin/), [Hongjin Qian](https://md.research.elamur.ai/free/en/authors/hongjin-qian/), [Shiyu Li](https://md.research.elamur.ai/free/en/authors/shiyu-li/), [Zhao Yang](https://md.research.elamur.ai/free/en/authors/zhao-yang/), [Yutao Zhu](https://md.research.elamur.ai/free/en/authors/yutao-zhu/), [Ji-Rong Wen](https://md.research.elamur.ai/free/en/authors/ji-rong-wen/) and [Zhicheng Dou](https://md.research.elamur.ai/free/en/authors/zhicheng-dou/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.1465/) · [PDF](https://aclanthology.org/2026.findings-acl.1465.pdf) · [DOI 10.18653/v1/2026.findings-acl.1465](https://doi.org/10.18653/v1/2026.findings-acl.1465) · [OpenAlex](https://openalex.org/W7166827842)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
LLM-based web agents often fail on real websites. They see only one page at a time, so they cannot infer how a site is organized. HTML or screenshot inputs also miss interface details such as collapsed menus. The authors argue that agents need external knowledge of the website, not only stronger policies. Their solution, called WASP (short for Web Agent Sitemap Protocol), is a sitemap built specifically for agents and available for consultation at each step. It works at two levels. Globally, it stores the site's navigation hierarchy as a tree for quick lookup. Locally, it enriches core pages with summaries, typical workflows, and per-block descriptions that include position and interaction hints. To build these sitemaps cheaply, they introduce LightASM. It crawls by function to keep only core pages, then uses a browser simulator and an LLM annotator to create the abstractions. On the live-web benchmarks WebWalker and WebVoyager, WASP raises success rates and cuts the number of steps without any additional training. This makes the approach practical and easy to maintain as an add-on service.

## Key points
- Two components:
  - **WASP**, a protocol and service with a global tree of site structure plus local page and block guidance.
  - **LightASM**, a lightweight construction pipeline using Playwright-based crawling, popup removal, page summaries and block annotations.
- Evaluated on WebWalker and WebVoyager, with accessibility-tree inputs and with screenshot plus set-of-marks inputs. Gains over Direct and ReAct baselines were consistent.
- On WebVoyager, success rose to 52.8% (vs. 44.1%) and 58.3% (vs. 47.2%). In one setting, average steps fell from 6.18 to 5.26.
- Ablation with Qwen-2.5-VL-72B:
  - Global knowledge matters most for WebWalker's navigation-heavy tasks.
  - Local knowledge drives fine-grained in-page interactions on WebVoyager.
- Sitemaps can be post-edited. For example, adding selection guidance to an iPhone comparison block fixed a failing task. The authors conclude that external website priors help more than inference-time reasoning such as ReAct.

*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

- [Renmin University of China](https://md.research.elamur.ai/free/en/universities/renmin-university-of-china/) — University, Beijing, China · 139 works · 17,752 citations
- [Beijing Academy of Artificial Intelligence](https://md.research.elamur.ai/free/en/labs/beijing-academy-of-artificial-intelligence/) — Research institute, Beijing, China · 46 works · 8,682 citations

📚 Shelves (2): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works

## Cite

Cite as: Yuyao Zhang, Hongyu Lu, Jiajie Jin, Hongjin Qian, Shiyu Li, Zhao Yang, Yutao Zhu, Ji-Rong Wen and Zhicheng Dou. 2026. Web Sitemap Knowledge Can Enhance Autonomous Browsing. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhang2026web,
  title = {{Web Sitemap Knowledge Can Enhance Autonomous Browsing}},
  author = {Yuyao Zhang, Hongyu Lu, Jiajie Jin, Hongjin Qian, Shiyu Li, Zhao Yang, Yutao Zhu, Ji-Rong Wen and Zhicheng Dou},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1465},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1465}
}
```

- [← previous Weakly-supervised Argument Mining with Boundary Refinement and Relation Denoising](https://md.research.elamur.ai/free/en/papers/sun-2026-weakly-supervised-argument-mining-boundary/)
- [next → WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoning](https://md.research.elamur.ai/free/en/papers/yu-2026-webanchor-anchoring-agent-planning-stabilize/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/56/)

## References

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

1. Arvind Arasu and Hector Garcia-Molina. 2003. Extracting structured data from web pages. In Proceedings of the 2003 ACM SIGMOD International Conference on Management of Data, pages 337–348. [find](https://scholar.google.com/scholar?q=Arvind+Arasu+and+Hector+Garcia%2DMolina%2E+2003%2E+Extracting+structured+data+from+web+pages%2E+In+Proceedings+of+the+2003+ACM+SIGMOD+International+Conference+on+Management+of+Data%2C+pages+337%E2%80%93348%2E)
2. Hyungjoo Chae, Namyoung Kim, Kai Tzu-iunn Ong, Minju Gwak, Gwanwoo Song, Jihoon Kim, Sunghwan Kim, Dongha Lee, and Jinyoung Yeo. 2024. Web agents with world models: Learning and leveraging environment dynamics in web navigation. CoRR, abs/2410.13232. — [arXiv:2410.13232](https://arxiv.org/abs/2410.13232) [find](https://scholar.google.com/scholar?q=Hyungjoo+Chae%2C+Namyoung+Kim%2C+Kai+Tzu%2Diunn+Ong%2C+Minju+Gwak%2C+Gwanwoo+Song%2C+Jihoon+Kim%2C+Sunghwan+Kim%2C+Dongha+Lee%2C+and+Jinyoung+Yeo%2E+2024%2E+Web+agents+with+world+models%3A+Learning+and+leveraging+environment)
3. Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Sam Stevens, Boshi Wang, Huan Sun, and Yu Su. 2023. [Mind2web: Towards a generalist agent for the web](https://md.research.elamur.ai/free/en/papers/deng-2023-mind2web-towards-generalist-agent-web/). In Advances in Neural Information Processing Systems, volume 36, pages 28091–28114. Curran Associates, Inc.
4. Tianqing Fang, Hongming Zhang, Zhisong Zhang, Kaixin Ma, Wenhao Yu, Haitao Mi, and Dong Yu. 2025. Webevolver: Enhancing web agent self-improvement with coevolving world model. [find](https://scholar.google.com/scholar?q=Tianqing+Fang%2C+Hongming+Zhang%2C+Zhisong+Zhang%2C+Kaixin+Ma%2C+Wenhao+Yu%2C+Haitao+Mi%2C+and+Dong+Yu%2E+2025%2E+Webevolver%3A+Enhancing+web+agent+self%2Dimprovement+with+coevolving+world+model%2E)
5. Yu Gu, Kai Zhang, Yuting Ning, Boyuan Zheng, Boyu Gou, Tianci Xue, Cheng Chang, Sanjari Srivastava, Yanan Xie, Peng Qi, Huan Sun, and Yu Su. 2025. Is your LLM secretly a world model of the internet? model-based planning for web agents. [find](https://scholar.google.com/scholar?q=Yu+Gu%2C+Kai+Zhang%2C+Yuting+Ning%2C+Boyuan+Zheng%2C+Boyu+Gou%2C+Tianci+Xue%2C+Cheng+Chang%2C+Sanjari+Srivastava%2C+Yanan+Xie%2C+Peng+Qi%2C+Huan+Sun%2C+and+Yu+Su%2E+2025%2E+Is+your+LLM+secretly+a+world+model+of+the+internet%3F+m)
6. Trans. Mach. Learn. Res., 2025. [find](https://scholar.google.com/scholar?q=Trans%2E+Mach%2E+Learn%2E+Res%2E%2C+2025%2E)
7. 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](https://md.research.elamur.ai/free/en/papers/he-2024-webvoyager-building-end-end-web/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), A…
8. Jing Yu Koh, Stephen McAleer, Daniel Fried, and Ruslan Salakhutdinov. 2024. [Tree search for language model agents](https://md.research.elamur.ai/free/en/papers/koh-2024-tree-search-language-model-agents/). CoRR, abs/2407.01476.
9. Nicholas Kushmerick. 2000. Wrapper verification. World Wide Web, 3(2):79–94. [find](https://scholar.google.com/scholar?q=Nicholas+Kushmerick%2E+2000%2E+Wrapper+verification%2E+World+Wide+Web%2C+3%282%29%3A79%E2%80%9394%2E)
10. Hanyu Lai, Xiao Liu, Iat Long Iong, Shuntian Yao, Yuxuan Chen, Pengbo Shen, Hao Yu, Hanchen Zhang, Xiaohan Zhang, Yuxiao Dong, and Jie Tang. 2024. [Autowebglm: A large language model-based web navigating agent](https://md.research.elamur.ai/free/en/papers/lai-2024-autowebglm-large-language-model-based/). In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, K…
11. Magnus Müller and Gregor Žunič. 2024. Browser use: Enable ai to control your browser. [find](https://scholar.google.com/scholar?q=Magnus+M%C3%BCller+and+Gregor+%C5%BDunic%CC%8C%2E+2024%2E+Browser+use%3A+Enable+ai+to+control+your+browser%2E)
12. OpenAI. 2024a. Browsecomp: a benchmark for browsing agents. Accessed: 2025-05-05. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2024a%2E+Browsecomp%3A+a+benchmark+for+browsing+agents%2E+Accessed%3A+2025%2D05%2D05%2E)
13. OpenAI. 2024b. Using a computer with an agent. Accessed: 2025-05-05. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2024b%2E+Using+a+computer+with+an+agent%2E+Accessed%3A+2025%2D05%2D05%2E)
14. Zehan Qi, Xiao Liu, Iat Long Iong, Hanyu Lai, Xueqiao Sun, Wenyi Zhao, Yu Yang, Xinyue Yang, Jiadai Sun, Shuntian Yao, Tianjie Zhang, Wei Xu, Jie Tang, and Yuxiao Dong. 2024. Webrl: Training LLM web agents via self-evolving online curriculum reinforcement learning. CoRR, abs/2411.02337. — [arXiv:2411.02337](https://arxiv.org/abs/2411.02337) [find](https://scholar.google.com/scholar?q=Zehan+Qi%2C+Xiao+Liu%2C+Iat+Long+Iong%2C+Hanyu+Lai%2C+Xueqiao+Sun%2C+Wenyi+Zhao%2C+Yu+Yang%2C+Xinyue+Yang%2C+Jiadai+Sun%2C+Shuntian+Yao%2C+Tianjie+Zhang%2C+Wei+Xu%2C+Jie+Tang%2C+and+Yuxiao+Dong%2E+2024%2E+Webrl%3A+Training+LLM+web+a)
15. Tianlin Shi, Andrej Karpathy, Linxi Fan, Jonathan Hernandez, and Percy Liang. 2017. World of bits: An open-domain platform for web-based agents. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017, volume 70 of Proceedings of M… [find](https://scholar.google.com/scholar?q=Tianlin+Shi%2C+Andrej+Karpathy%2C+Linxi+Fan%2C+Jonathan+Hernandez%2C+and+Percy+Liang%2E+2017%2E+World+of+bits%3A+An+open%2Ddomain+platform+for+web%2Dbased+agents%2E+In+Proceedings+of+the+34th+International+Conference+on+)
16. Paloma Sodhi, SRK Branavan, Yoav Artzi, and Ryan McDonald. 2023. Step: Stacked llm policies for web actions. arXiv preprint arXiv:2310.03720. — [arXiv:2310.03720](https://arxiv.org/abs/2310.03720) [find](https://scholar.google.com/scholar?q=Paloma+Sodhi%2C+SRK+Branavan%2C+Yoav+Artzi%2C+and+Ryan+McDonald%2E+2023%2E+Step%3A+Stacked+llm+policies+for+web+actions%2E+arXiv+preprint+arXiv%3A2310%2E03720%2E+%E2%80%94+%5BarXiv%3A2310%2E03720%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2310%2E03720%29)
17. Yueqi Song, Frank Xu, Shuyan Zhou, and Graham Neubig. 2025. Beyond browsing: Api-based web agents. [find](https://scholar.google.com/scholar?q=Yueqi+Song%2C+Frank+Xu%2C+Shuyan+Zhou%2C+and+Graham+Neubig%2E+2025%2E+Beyond+browsing%3A+Api%2Dbased+web+agents%2E)
18. Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, and Graham Neubig. 2025. [Agent workflow memory](https://md.research.elamur.ai/free/en/papers/wang-2024-agent-workflow-memory/). In Forty-second International Conference on Machine Learning, ICML 2025, Vancouver, BC, Canada, July 13-19, 2025, Proceedings of Machine Learning Research. PMLR / OpenReview.net.
19. Jialong Wu, Wenbiao Yin, Yong Jiang, Zhenglin Wang, Zekun Xi, Runnan Fang, Linhai Zhang, Yulan He, Deyu Zhou, Pengjun Xie, and Fei Huang. 2025. [Webwalker: Benchmarking llms in web traversal](https://md.research.elamur.ai/free/en/papers/wu-2025-webwalker-benchmarking-llms-web-traversal/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pa…
20. Tianci Xue, Weijian Qi, Tianneng Shi, Chan Hee Song, Boyu Gou, Dawn Song, Huan Sun, and Yu Su. 2025a. An illusion of progress? assessing the current state of web agents. [find](https://scholar.google.com/scholar?q=Tianci+Xue%2C+Weijian+Qi%2C+Tianneng+Shi%2C+Chan+Hee+Song%2C+Boyu+Gou%2C+Dawn+Song%2C+Huan+Sun%2C+and+Yu+Su%2E+2025a%2E+An+illusion+of+progress%3F+assessing+the+current+state+of+web+agents%2E)
21. Tianci Xue, Weijian Qi, Tianneng Shi, Chan Hee Song, Boyu Gou, Dawn Song, Huan Sun, and Yu Su. 2025b. An illusion of progress? assessing the current state of web agents. [find](https://scholar.google.com/scholar?q=Tianci+Xue%2C+Weijian+Qi%2C+Tianneng+Shi%2C+Chan+Hee+Song%2C+Boyu+Gou%2C+Dawn+Song%2C+Huan+Sun%2C+and+Yu+Su%2E+2025b%2E+An+illusion+of+progress%3F+assessing+the+current+state+of+web+agents%2E)
22. Shunyu Yao, Howard Chen, John Yang, and Karthik Narasimhan. 2022. [Webshop: Towards scalable real-world web interaction with grounded language agents](https://md.research.elamur.ai/free/en/papers/yao-2022-webshop-towards-scalable-real-world/). In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, L…
23. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R. Narasimhan, and Yuan Cao. 2023. [React: Synergizing reasoning and acting in language models](https://md.research.elamur.ai/free/en/papers/yao-2022-react-synergizing-reasoning-acting-language/). In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net.
24. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Zhipeng Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, Peiyu Liu, Jian-Yun Nie, and Ji-Rong Wen. 2025. [A survey of l…](https://md.research.elamur.ai/free/en/papers/zhao-2023-survey-large-language-models/)
25. Boyuan Zheng, Michael Y. Fatemi, Xiaolong Jin, Zora Zhiruo Wang, Apurva Gandhi, Yueqi Song, Yu Gu, Jayanth Srinivasa, Gaowen Liu, Graham Neubig, and Yu Su. 2025. Skillweaver: Web agents can self-improve by discovering and honing skills. [find](https://scholar.google.com/scholar?q=Boyuan+Zheng%2C+Michael+Y%2E+Fatemi%2C+Xiaolong+Jin%2C+Zora+Zhiruo+Wang%2C+Apurva+Gandhi%2C+Yueqi+Song%2C+Yu+Gu%2C+Jayanth+Srinivasa%2C+Gaowen+Liu%2C+Graham+Neubig%2C+and+Yu+Su%2E+2025%2E+Skillweaver%3A+Web+agents+can+self%2Dimpro)
26. Longtao Zheng, Rundong Wang, Xinrun Wang, and Bo An. 2024. Synapse: Trajectory-as-exemplar prompting with memory for computer control. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. [find](https://scholar.google.com/scholar?q=Longtao+Zheng%2C+Rundong+Wang%2C+Xinrun+Wang%2C+and+Bo+An%2E+2024%2E+Synapse%3A+Trajectory%2Das%2Dexemplar+prompting+with+memory+for+computer+control%2E+In+The+Twelfth+International+Conference+on+Learning+Representatio)
27. 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](https://md.research.elamur.ai/free/en/papers/zhou-2023-webarena-realistic-web-environment-building/). In The Twelfth International Conference on Learning Representation…

*Updated 2 November 2026*