---
title: "WebClipper — paper by Wang et al. (2026) — summary and ideas"
description: "The paper also introduces the F-AE Score, a single metric for the accuracy–efficiency balance that is relevant to cost-aware… 42 references."
authors: ["Junjie Wang", "Zequn Xie", "Dan Yang", "Jie Feng", "Yue Shen", "Duolin Sun", "Meixiu Long", "Yihan Jiao", "Zhehao Tan", "Jian Wang", "Peng Wei", "Jinjie Gu"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.988/"
doi: "10.18653/v1/2026.acl-long.988"
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/wang-2026-webclipper-efficient-evolution-web-agents/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2026-webclipper-efficient-evolution-web-agents/)

[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/47/) / WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning

# WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning

**Authors:** [Junjie Wang](https://md.research.elamur.ai/free/en/authors/junjie-wang/), [Zequn Xie](https://md.research.elamur.ai/free/en/authors/zequn-xie/), [Dan Yang](https://md.research.elamur.ai/free/en/authors/dan-yang/), [Jie Feng](https://md.research.elamur.ai/free/en/authors/jie-feng/), [Yue Shen](https://md.research.elamur.ai/free/en/authors/yue-shen/), [Duolin Sun](https://md.research.elamur.ai/free/en/authors/duolin-sun/), [Meixiu Long](https://md.research.elamur.ai/free/en/authors/meixiu-long/), [Yihan Jiao](https://md.research.elamur.ai/free/en/authors/yihan-jiao/), [Zhehao Tan](https://md.research.elamur.ai/free/en/authors/zhehao-tan/), [Jian Wang](https://md.research.elamur.ai/free/en/authors/jian-wang/), Peng Wei and [Jinjie Gu](https://md.research.elamur.ai/free/en/authors/jinjie-gu/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/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.acl-long.988/) · [PDF](https://aclanthology.org/2026.acl-long.988.pdf) · [DOI 10.18653/v1/2026.acl-long.988](https://doi.org/10.18653/v1/2026.acl-long.988) · [OpenAlex](https://openalex.org/W7166836367)

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

## Summary
Open-source Deep Research web agents such as Tongyi-DeepResearch and MiroThinker reach high accuracy on complex information-seeking tasks. They get there through very long tool-call sequences, which makes them slow and costly when search APIs are paid. The authors trace much of this waste to two habits: re-fetching facts the agent already has (cyclic loops) and chasing leads that never feed into the answer (dead-end branches). WebClipper turns each trajectory into a graph of action and information nodes. It then extracts an approximate minimum-necessary DAG linking the query to the final answer and drops every step outside it. The agent's thoughts on the shortened path are rewritten with awareness of prior context so the reasoning stays coherent. The existing agent is then fine-tuned further on these cleaned trajectories instead of being trained from scratch. On several benchmarks, this cuts tool-call rounds and token usage by about a fifth while matching or improving accuracy. The paper also introduces the F-AE Score, a single metric for the accuracy–efficiency balance that is relevant to cost-aware deployment.

## Key points
- The pipeline has four stages: state-graph construction, approximate MNDAG mining for pruning, coherence-aware thought rewriting, and agent evolution in two variants. WebClipper(Eff) gives the lowest cost, and WebClipper(Hybrid) offers the best overall trade-off and F-AE.
- Training QA pairs come from WebShaper, WebDancer, WebExplorer, TaskCraft and Voyager. Trajectories are sampled from a ReAct-style base agent and kept only when the query's pass rate satisfies 0 \< PR(q) ≤ 0.5.
- Tool-call rounds and tokens drop by about 20% overall, and on GAIA the reduction is about 30%. The authors partly explain the GAIA result by its roughly 15% share of puzzle-like questions that need little tool use.
- A plain self-distillation baseline (Unpruned-Distill) raises accuracy but also increases the number of tool calls.
- In the ablations, removing graph pruning or PPL-based rewrite selection lowers results. Rewriting all thoughts without historical context causes performance to collapse.

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

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works

🧭 Topics (1): [🪶 Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/) · 242 works

## Cite

Cite as: Junjie Wang, Zequn Xie, Dan Yang, Jie Feng, Yue Shen, Duolin Sun, Meixiu Long, Yihan Jiao, Zhehao Tan, Jian Wang, Peng Wei and Jinjie Gu. 2026. WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{wang2026webclipper,
  title = {{WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning}},
  author = {Junjie Wang, Zequn Xie, Dan Yang, Jie Feng, Yue Shen, Duolin Sun, Meixiu Long, Yihan Jiao, Zhehao Tan, Jian Wang, Peng Wei and Jinjie Gu},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.988},
  url = {https://doi.org/10.18653/v1/2026.acl-long.988}
}
```

- [← 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 → WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics](https://md.research.elamur.ai/free/en/papers/liu-2026-webcoderbench-benchmarking-web-application-generation/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/47/)

## References

42 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Pranjal Aggarwal and Sean Welleck. 2025. [L1: Controlling how long a reasoning model thinks with reinforcement learning](https://md.research.elamur.ai/free/en/papers/aggarwal-2025-l1-controlling-long-reasoning-model/). Preprint, arXiv:2503.04697.
2. Renat Aksitov, Sobhan Miryoosefi, Zonglin Li, Daliang Li, Sheila Babayan, Kavya Kopparapu, Zachary Fisher, Ruiqi Guo, Sushant Prakash, Pranesh Srinivasan, and 1 others. 2023. Rest meets react: Self-improvement for multi-step reasoning llm agent. arXiv preprint arXiv:2312.10003. via model, context, a… — [arXiv:2312.10003](https://arxiv.org/abs/2312.10003) [find](https://scholar.google.com/scholar?q=Renat+Aksitov%2C+Sobhan+Miryoosefi%2C+Zonglin+Li%2C+Daliang+Li%2C+Sheila+Babayan%2C+Kavya+Kopparapu%2C+Zachary+Fisher%2C+Ruiqi+Guo%2C+Sushant+Prakash%2C+Pranesh+Srinivasan%2C+and+1+others%2E+2023%2E+Rest+meets+react%3A+Self%2Dim)
3. Yifan Bai, Yiping Bao, Guanduo Chen, Jiahao Chen, Ningxin Chen, Ruijue Chen, Yanru Chen, Yuankun Chen, Yutian Chen, Zhuofu Chen, Jialei Cui, Hao Ding, Mengnan Dong, Angang Du, Chenzhuang Du, Dikang Du, Yulun Du, Yu Fan, Yichen Feng, and 149 others. 2025b. [Kimi k2: Open agentic intelligence](https://md.research.elamur.ai/free/en/papers/kimi-team-2025-kimi-k2-open-agentic/). Preprint…
4. Mingyang Chen, Linzhuang Sun, Tianpeng Li, Haoze Sun, Yijie Zhou, Chenzheng Zhu, Haofen Wang, Jeff Z. Pan, Wen Zhang, Huajun Chen, Fan Yang, Zenan Zhou, and Weipeng Chen. 2025. Research: Learning to reason with search for llms via reinforcement learning. Preprint, arXiv:2503.19470. [find](https://scholar.google.com/scholar?q=Mingyang+Chen%2C+Linzhuang+Sun%2C+Tianpeng+Li%2C+Haoze+Sun%2C+Yijie+Zhou%2C+Chenzheng+Zhu%2C+Haofen+Wang%2C+Jeff+Z%2E+Pan%2C+Wen+Zhang%2C+Huajun+Chen%2C+Fan+Yang%2C+Zenan+Zhou%2C+and+Weipeng+Chen%2E+2025%2E+Research%3A+Learning+to+r)
5. Claude Team. 2025. Claude research. [find](https://scholar.google.com/scholar?q=Claude+Team%2E+2025%2E+Claude+research%2E)
6. Yingqian Cui, Pengfei He, Jingying Zeng, Hui Liu, Xianfeng Tang, Zhenwei Dai, Yan Han, Chen Luo, Jing Huang, Zhen Li, Suhang Wang, Yue Xing, Jiliang Tang, and Qi He. 2025. Stepwise perplexity-guided refinement for efficient chain-of-thought reasoning in large language models. In Findings of the Asso… [find](https://scholar.google.com/scholar?q=Yingqian+Cui%2C+Pengfei+He%2C+Jingying+Zeng%2C+Hui+Liu%2C+Xianfeng+Tang%2C+Zhenwei+Dai%2C+Yan+Han%2C+Chen+Luo%2C+Jing+Huang%2C+Zhen+Li%2C+Suhang+Wang%2C+Yue+Xing%2C+Jiliang+Tang%2C+and+Qi+He%2E+2025%2E+Stepwise+perplexity%2Dguided+r)
7. Razvan-Gabriel Dumitru, Darius Peteleaza, Vikas Yadav, and Liangming Pan. 2025. ConciseRL: Conciseness-guided reinforcement learning for efficient reasoning models. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 17099–17123, Suzhou, China. Association for Computation… [find](https://scholar.google.com/scholar?q=Razvan%2DGabriel+Dumitru%2C+Darius+Peteleaza%2C+Vikas+Yadav%2C+and+Liangming+Pan%2E+2025%2E+ConciseRL%3A+Conciseness%2Dguided+reinforcement+learning+for+efficient+reasoning+models%2E+In+Findings+of+the+Association+for+)
8. Gemini Team. 2025. Gemini deep research. [find](https://scholar.google.com/scholar?q=Gemini+Team%2E+2025%2E+Gemini+deep+research%2E)
9. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, and 1 others. 2025. [DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948.
10. Tingxu Han, Zhenting Wang, Chunrong Fang, Shiyu Zhao, Shiqing Ma, and Zhenyu Chen. 2025. [Token-budget-aware LLM reasoning](https://md.research.elamur.ai/free/en/papers/han-2024-token-budget-aware-llm-reasoning/). In Findings of the Association for Computational Linguistics: ACL 2025, pages 24842–24855, Vienna, Austria. Association for Computational Linguistics. anthropic. 2025. Introduci…
11. David J Hand, Peter Christen, and Nishadi Kirielle. 2021. F*: an interpretable transformation of the f-measure. Machine learning, 110(3):451–456. [find](https://scholar.google.com/scholar?q=David+J+Hand%2C+Peter+Christen%2C+and+Nishadi+Kirielle%2E+2021%2E+F%2A%3A+an+interpretable+transformation+of+the+f%2Dmeasure%2E+Machine+learning%2C+110%283%29%3A451%E2%80%93456%2E)
12. Song Bai, Lidong Bing, Carson Chen, Guanzheng Chen, Yuntao Chen, Zhe Chen, Ziyi Chen, Jifeng Dai, Xuan Dong, Wenhan Dou, Yue Deng, Yunjie Fu, Junqi Ge, Chenxia Han, Tammy Huang, Zhenhang Huang, Jerry Jiao, Shilei Jiang, Tianyu Jiao, and 35 others. 2025a. Mirothinker: Pushing the performance boundari… — [arXiv:2512.20491](https://arxiv.org/abs/2512.20491) [find](https://scholar.google.com/scholar?q=Song+Bai%2C+Lidong+Bing%2C+Carson+Chen%2C+Guanzheng+Chen%2C+Yuntao+Chen%2C+Zhe+Chen%2C+Ziyi+Chen%2C+Jifeng+Dai%2C+Xuan+Dong%2C+Wenhan+Dou%2C+Yue+Deng%2C+Yunjie+Fu%2C+Junqi+Ge%2C+Chenxia+Han%2C+Tammy+Huang%2C+Zhenhang+Huang%2C+Jerry+)
13. OpenAI. 2024. Learning to reason with LLMs. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2024%2E+Learning+to+reason+with+LLMs%2E)
14. Baixuan Li, Bo Zhang, Dingchu Zhang, Fei Huang, Guangyu Li, Guoxin Chen, Huifeng Yin, Jialong Wu, Jingren Zhou, Kuan Li, Liangcai Su, Litu Ou, Liwen Zhang, Pengjun Xie, Rui Ye, Wenbiao Yin, Xinmiao Yu, Xinyu Wang, Xixi Wu, and 37 others. 2025a. Tongyi deepresearch technical report. Preprint, arXiv:2… — [arXiv:2510.24701](https://arxiv.org/abs/2510.24701) [find](https://scholar.google.com/scholar?q=Baixuan+Li%2C+Bo+Zhang%2C+Dingchu+Zhang%2C+Fei+Huang%2C+Guangyu+Li%2C+Guoxin+Chen%2C+Huifeng+Yin%2C+Jialong+Wu%2C+Jingren+Zhou%2C+Kuan+Li%2C+Liangcai+Su%2C+Litu+Ou%2C+Liwen+Zhang%2C+Pengjun+Xie%2C+Rui+Ye%2C+Wenbiao+Yin%2C+Xinmiao+Yu)
15. OpenAI. 2025a. Deep research system card. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025a%2E+Deep+research+system+card%2E)
16. Kuan Li, Zhongwang Zhang, Huifeng Yin, Liwen Zhang, Litu Ou, Jialong Wu, Wenbiao Yin, Baixuan Li, Zhengwei Tao, Xinyu Wang, Weizhou Shen, Junkai Zhang, Dingchu Zhang, Xixi Wu, Yong Jiang, Ming Yan, Pengjun Xie, Fei Huang, and Jingren Zhou. 2025b. Websailor: Navigating super-human reasoning for web a… [find](https://scholar.google.com/scholar?q=Kuan+Li%2C+Zhongwang+Zhang%2C+Huifeng+Yin%2C+Liwen+Zhang%2C+Litu+Ou%2C+Jialong+Wu%2C+Wenbiao+Yin%2C+Baixuan+Li%2C+Zhengwei+Tao%2C+Xinyu+Wang%2C+Weizhou+Shen%2C+Junkai+Zhang%2C+Dingchu+Zhang%2C+Xixi+Wu%2C+Yong+Jiang%2C+Ming+Yan%2C+Pe)
17. Xiaoxi Li, Jiajie Jin, Guanting Dong, Hongjin Qian, Yongkang Wu, Ji-Rong Wen, Yutao Zhu, and Zhicheng Dou. 2025c. Webthinker: Empowering large reasoning models with deep research capability. Preprint, arXiv:2504.21776. [find](https://scholar.google.com/scholar?q=Xiaoxi+Li%2C+Jiajie+Jin%2C+Guanting+Dong%2C+Hongjin+Qian%2C+Yongkang+Wu%2C+Ji%2DRong+Wen%2C+Yutao+Zhu%2C+and+Zhicheng+Dou%2E+2025c%2E+Webthinker%3A+Empowering+large+reasoning+models+with+deep+research+capability%2E+Preprint%2C)
18. Zijian Li, Xin Guan, Bo Zhang, Shen Huang, Houquan Zhou, Shaopeng Lai, Ming Yan, Yong Jiang, Pengjun Xie, Fei Huang, Jun Zhang, and Jingren Zhou. 2025d. Webweaver: Structuring web-scale evidence with dynamic outlines for open-ended deep research. Preprint, arXiv:2509.13312. — [arXiv:2509.13312](https://arxiv.org/abs/2509.13312) [find](https://scholar.google.com/scholar?q=Zijian+Li%2C+Xin+Guan%2C+Bo+Zhang%2C+Shen+Huang%2C+Houquan+Zhou%2C+Shaopeng+Lai%2C+Ming+Yan%2C+Yong+Jiang%2C+Pengjun+Xie%2C+Fei+Huang%2C+Jun+Zhang%2C+and+Jingren+Zhou%2E+2025d%2E+Webweaver%3A+Structuring+web%2Dscale+evidence+with+)
19. Junteng Liu, Yunji Li, Chi Zhang, Jingyang Li, Aili Chen, Ke Ji, Weiyu Cheng, Zijia Wu, Chengyu Du, Qidi Xu, Jiayuan Song, Zhengmao Zhu, Wenhu Chen, Pengyu Zhao, and Junxian He. 2025. Webexplorer: Explore and evolve for training long-horizon web agents. Preprint, arXiv:2509.06501. — [arXiv:2509.06501](https://arxiv.org/abs/2509.06501) [find](https://scholar.google.com/scholar?q=Junteng+Liu%2C+Yunji+Li%2C+Chi+Zhang%2C+Jingyang+Li%2C+Aili+Chen%2C+Ke+Ji%2C+Weiyu+Cheng%2C+Zijia+Wu%2C+Chengyu+Du%2C+Qidi+Xu%2C+Jiayuan+Song%2C+Zhengmao+Zhu%2C+Wenhu+Chen%2C+Pengyu+Zhao%2C+and+Junxian+He%2E+2025%2E+Webexplorer%3A+Exp)
20. Haotian Luo, Li Shen, Haiying He, Yibo Wang, Shiwei Liu, Wei Li, Naiqiang Tan, Xiaochun Cao, and Dacheng Tao. 2025. O1-pruner: Length-harmonizing fine-tuning for o1-like reasoning pruning. Preprint, arXiv:2501.12570. [find](https://scholar.google.com/scholar?q=Haotian+Luo%2C+Li+Shen%2C+Haiying+He%2C+Yibo+Wang%2C+Shiwei+Liu%2C+Wei+Li%2C+Naiqiang+Tan%2C+Xiaochun+Cao%2C+and+Dacheng+Tao%2E+2025%2E+O1%2Dpruner%3A+Length%2Dharmonizing+fine%2Dtuning+for+o1%2Dlike+reasoning+pruning%2E+Preprint%2C+a)
21. Xinyin Ma, Guangnian Wan, Runpeng Yu, Gongfan Fang, and Xinchao Wang. 2025. [CoT-valve: Length-compressible chain-of-thought tuning](https://md.research.elamur.ai/free/en/papers/ma-2025-cot-valve-length-compressible-chain/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6025–6035, Vienna, Austria. Association for Co…
22. Grégoire Mialon, Clémentine Fourrier, Thomas Wolf, Yann LeCun, and Thomas Scialom. 2023. [Gaia: a benchmark for general ai assistants](https://md.research.elamur.ai/free/en/papers/mialon-2023-gaia-benchmark-general-ai-assistants/). In The Twelfth International Conference on Learning Representations.
23. Tergel Munkhbat, Namgyu Ho, Seo Hyun Kim, Yongjin Yang, Yujin Kim, and Se-Young Yun. 2025. Self-training elicits concise reasoning in large language models. In Findings of the Association for Computational Linguistics: ACL 2025, pages 25127–25152, Vienna, Austria. Association for Computational Lingu… [find](https://scholar.google.com/scholar?q=Tergel+Munkhbat%2C+Namgyu+Ho%2C+Seo+Hyun+Kim%2C+Yongjin+Yang%2C+Yujin+Kim%2C+and+Se%2DYoung+Yun%2E+2025%2E+Self%2Dtraining+elicits+concise+reasoning+in+large+language+models%2E+In+Findings+of+the+Association+for+Computat)
24. OpenAI. 2025b. Introducing openai o3 and o4-mini. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025b%2E+Introducing+openai+o3+and+o4%2Dmini%2E)
25. Long Phan, Alice Gatti, Ziwen Han, Nathaniel Li, Josephina Hu, Hugh Zhang, Chen Bo Calvin Zhang, Mohamed Shaaban, John Ling, Sean Shi, and 1 others. 2025. [Humanity’s last exam](https://md.research.elamur.ai/free/en/papers/phan-2025-humanity-s-last-exam/). arXiv preprint arXiv:2501.14249.
26. Soham Poddar, Paramita Koley, Janardan Misra, Niloy Ganguly, and Saptarshi Ghosh. 2025. Brevity is the soul of sustainability: Characterizing LLM response lengths. In Findings of the Association for Computational Linguistics: ACL 2025, pages 21848–21864, Vienna, Austria. Association for Computationa… [find](https://scholar.google.com/scholar?q=Soham+Poddar%2C+Paramita+Koley%2C+Janardan+Misra%2C+Niloy+Ganguly%2C+and+Saptarshi+Ghosh%2E+2025%2E+Brevity+is+the+soul+of+sustainability%3A+Characterizing+LLM+response+lengths%2E+In+Findings+of+the+Association+for+C)
27. GPT Research. 2025a. Gpt research. [find](https://scholar.google.com/scholar?q=GPT+Research%2E+2025a%2E+Gpt+research%2E)
28. Open Deep Research. 2025b. Open deep research. [find](https://scholar.google.com/scholar?q=Open+Deep+Research%2E+2025b%2E+Open+deep+research%2E)
29. SerpAPI. 2025. Serpapi: Google search api. [find](https://scholar.google.com/scholar?q=SerpAPI%2E+2025%2E+Serpapi%3A+Google+search+api%2E)
30. Dingfeng Shi, Jingyi Cao, Qianben Chen, Weichen Sun, Weizhen Li, Hongxuan Lu, Fangchen Dong, Tianrui Qin, King Zhu, Minghao Liu, Jian Yang, Ge Zhang, Jiaheng Liu, Changwang Zhang, Jun Wang, Yuchen Eleanor Jiang, and Wangchunshu Zhou. 2025. Taskcraft: Automated generation of agentic tasks. Preprint,… — [arXiv:2506.10055](https://arxiv.org/abs/2506.10055) [find](https://scholar.google.com/scholar?q=Dingfeng+Shi%2C+Jingyi+Cao%2C+Qianben+Chen%2C+Weichen+Sun%2C+Weizhen+Li%2C+Hongxuan+Lu%2C+Fangchen+Dong%2C+Tianrui+Qin%2C+King+Zhu%2C+Minghao+Liu%2C+Jian+Yang%2C+Ge+Zhang%2C+Jiaheng+Liu%2C+Changwang+Zhang%2C+Jun+Wang%2C+Yuchen+Ele)
31. Zhengwei Tao, Haiyang Shen, Baixuan Li, Wenbiao Yin, Jialong Wu, Kuan Li, Zhongwang Zhang, Huifeng Yin, Rui Ye, Liwen Zhang, Xinyu Wang, Pengjun Xie, Jingren Zhou, and Yong Jiang. 2025a. We-bleaper: Empowering efficiency and efficacy in webagent via enabling info-rich seeking. Preprint, arXiv:2510.2… — [arXiv:2510.24697](https://arxiv.org/abs/2510.24697) [find](https://scholar.google.com/scholar?q=Zhengwei+Tao%2C+Haiyang+Shen%2C+Baixuan+Li%2C+Wenbiao+Yin%2C+Jialong+Wu%2C+Kuan+Li%2C+Zhongwang+Zhang%2C+Huifeng+Yin%2C+Rui+Ye%2C+Liwen+Zhang%2C+Xinyu+Wang%2C+Pengjun+Xie%2C+Jingren+Zhou%2C+and+Yong+Jiang%2E+2025a%2E+We%2Dbleaper%3A+E)
32. Zhengwei Tao, Jialong Wu, Wenbiao Yin, Junkai Zhang, Baixuan Li, Haiyang Shen, Kuan Li, Liwen Zhang, Xinyu Wang, Yong Jiang, Pengjun Xie, Fei Huang, and Jingren Zhou. 2025b. Webshaper: Agentically data synthesizing via information-seeking formalization. Preprint, arXiv:2507.15061. — [arXiv:2507.15061](https://arxiv.org/abs/2507.15061) [find](https://scholar.google.com/scholar?q=Zhengwei+Tao%2C+Jialong+Wu%2C+Wenbiao+Yin%2C+Junkai+Zhang%2C+Baixuan+Li%2C+Haiyang+Shen%2C+Kuan+Li%2C+Liwen+Zhang%2C+Xinyu+Wang%2C+Yong+Jiang%2C+Pengjun+Xie%2C+Fei+Huang%2C+and+Jingren+Zhou%2E+2025b%2E+Webshaper%3A+Agentically+dat)
33. Junjie Wang, Mingyang Chen, Binbin Hu, Dan Yang, Ziqi Liu, Yue Shen, Peng Wei, Zhiqiang Zhang, Jinjie Gu, Jun Zhou, Jeff Z. Pan, Wen Zhang, and Huajun Chen. 2024. Learning to plan for retrieval-augmented large language models from knowledge graphs. In Findings of the Association for Computational Li… [find](https://scholar.google.com/scholar?q=Junjie+Wang%2C+Mingyang+Chen%2C+Binbin+Hu%2C+Dan+Yang%2C+Ziqi+Liu%2C+Yue+Shen%2C+Peng+Wei%2C+Zhiqiang+Zhang%2C+Jinjie+Gu%2C+Jun+Zhou%2C+Jeff+Z%2E+Pan%2C+Wen+Zhang%2C+and+Huajun+Chen%2E+2024%2E+Learning+to+plan+for+retrieval%2Daugmen)
34. Jason Wei, Zhiqing Sun, Spencer Papay, Scott McKinney, Jeffrey Han, Isa Fulford, Hyung Won Chung, Alex Tachard Passos, William Fedus, and Amelia Glaese. 2025. Browsecomp: A simple yet challenging benchmark for browsing agents. arXiv preprint arXiv:2504.12516. 21655 10 [find](https://scholar.google.com/scholar?q=Jason+Wei%2C+Zhiqing+Sun%2C+Spencer+Papay%2C+Scott+McKinney%2C+Jeffrey+Han%2C+Isa+Fulford%2C+Hyung+Won+Chung%2C+Alex+Tachard+Passos%2C+William+Fedus%2C+and+Amelia+Glaese%2E+2025%2E+Browsecomp%3A+A+simple+yet+challenging+benc)
35. Jialong Wu, Baixuan Li, Runnan Fang, Wenbiao Yin, Liwen Zhang, Zhengwei Tao, Dingchu Zhang, Zekun Xi, Gang Fu, Yong Jiang, Pengjun Xie, Fei Huang, and Jingren Zhou. 2025. [Webdancer: Towards autonomous information seeking agency](https://md.research.elamur.ai/free/en/papers/wu-2025-webdancer-towards-autonomous-information-seeking/). Preprint, arXiv:2505.22648.
36. Xbench Team. 2025. Xbench-deepsearch. [find](https://scholar.google.com/scholar?q=Xbench+Team%2E+2025%2E+Xbench%2Ddeepsearch%2E)
37. Siheng Xiong, Oguzhan Gungordu, Blair Johnson, James C Kerce, and Faramarz Fekri. 2026. Scaling search-augmented llm reasoning via adaptive information control. arXiv preprint arXiv:2602.01672. — [arXiv:2602.01672](https://arxiv.org/abs/2602.01672) [find](https://scholar.google.com/scholar?q=Siheng+Xiong%2C+Oguzhan+Gungordu%2C+Blair+Johnson%2C+James+C+Kerce%2C+and+Faramarz+Fekri%2E+2026%2E+Scaling+search%2Daugmented+llm+reasoning+via+adaptive+information+control%2E+arXiv+preprint+arXiv%3A2602%2E01672%2E+%E2%80%94+%5BarX)
38. Silei Xu, Wenhao Xie, Lingxiao Zhao, and Pengcheng He. 2025. Chain of draft: Thinking faster by writing less. Preprint, arXiv:2502.18600. [find](https://scholar.google.com/scholar?q=Silei+Xu%2C+Wenhao+Xie%2C+Lingxiao+Zhao%2C+and+Pengcheng+He%2E+2025%2E+Chain+of+draft%3A+Thinking+faster+by+writing+less%2E+Preprint%2C+arXiv%3A2502%2E18600%2E)
39. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). Preprint, arXiv:2505.09388.
40. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik 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 International Conference on Learning Representations (ICLR).
41. Howard Yen, Ashwin Paranjape, Mengzhou Xia, The-jas Venkatesh, Jack Hessel, Danqi Chen, and Yuhao Zhang. 2025. Lost in the maze: Overcoming context limitations in long-horizon agentic search. arXiv preprint arXiv:2510.18939. [find](https://scholar.google.com/scholar?q=Howard+Yen%2C+Ashwin+Paranjape%2C+Mengzhou+Xia%2C+The%2Djas+Venkatesh%2C+Jack+Hessel%2C+Danqi+Chen%2C+and+Yuhao+Zhang%2E+2025%2E+Lost+in+the+maze%3A+Overcoming+context+limitations+in+long%2Dhorizon+agentic+search%2E+arXiv+pr)
42. Aohan Zeng, Xin Lv, Qinkai Zheng, Zhenyu Hou, Bin Chen, Chengxing Xie, Cunxiang Wang, Da Yin, Hao Zeng, Jiajie Zhang, Kedong Wang, Lucen Zhong, Mingdao Liu, Rui Lu, Shulin Cao, Xiaohan Zhang, Xuancheng Huang, Yao Wei, Yean Cheng, and 151 others. 2025. [Glm-4.5: Agentic, reasoning, and coding (arc) fo…](https://md.research.elamur.ai/free/en/papers/team-2025-4-glm-4-5-agentic/)

*Updated 1 November 2026*