---
title: "Empowering GUI Agents via Autonomous Experience Exploration"
description: "The authors propose PEEU, which needs only a website URL. 30.6% accuracy. 50 references."
authors: ["Tianyi Men", "Zhuoran Jin", "Pengfei Cao", "Yubo Chen", "Kang Liu", "Jun Zhao"]
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.1670/"
doi: "10.18653/v1/2026.acl-long.1670"
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/men-2026-empowering-gui-agents-autonomous-experience/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/men-2026-empowering-gui-agents-autonomous-experience/)

[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/31/) / Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning

# Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning

**Authors:** Tianyi Men, [Zhuoran Jin](https://md.research.elamur.ai/free/en/authors/zhuoran-jin/), [Pengfei Cao](https://md.research.elamur.ai/free/en/authors/pengfei-cao/), [Yubo Chen](https://md.research.elamur.ai/free/en/authors/yubo-chen/), [Kang Liu](https://md.research.elamur.ai/free/en/authors/kang-liu/) and [Jun Zhao](https://md.research.elamur.ai/free/en/authors/jun-zhao/) · **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.1670/) · [PDF](https://aclanthology.org/2026.acl-long.1670.pdf) · [DOI 10.18653/v1/2026.acl-long.1670](https://doi.org/10.18653/v1/2026.acl-long.1670) · [OpenAlex](https://openalex.org/W7166838629)

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

## Summary
Small open-source multimodal LLMs are cheaper than commercial models and keep data private, but as web agents they plan poorly and transfer badly to unfamiliar websites. The authors propose PEEU, which needs only a website URL. First, an explorer model reads the homepage, sets its own goals suited to the site, and runs goal-driven exploration that produces a tree of screens and actions. Second, the system compares the states before and after each action to extract atomic experiences. It then uses hindsight to rewrite each task so that it describes what the trajectory actually achieved, adding constraints only discovered during exploration. The resulting task–trajectory pairs train small models with SFT or GRPO. The authors also introduce TDHAF, a framework that tests compositional generalization across low, mid and high task levels, both in-domain and out-of-domain. On seven unseen real websites, and with data scale held equal across methods, PEEU beats prior approaches. The results suggest that aligned high-level data, not atomic skills, drives transferable planning.

## Key points
- PEEU on Qwen2.5-VL-7B reaches 30.6% accuracy on seven unseen websites, up from 7.8% for the Instruct model, and it outperforms Qwen2.5-VL-32B.
- Hindsight relabeling targets two flaws of coarse high-level tasks:
  - tasks and trajectories that do not match (for example, a task asking for 4.5+ stars while the trajectory reaches a 4-star item);
  - missing constraints, such as ingredients or cooking directions, that only become visible after exploring the site.
- TDHAF in-domain coverage (the share of tasks where all levels succeed):
  - Qwen2.5-VL-3B: 44.8% with high-level training, 22.7% with mid-level and 3.2% with low-level;
  - Qwen2.5-VL-7B: 51.9%, 36.4% and 9.1% respectively.
- TDHAF out-of-domain coverage:
  - 3B: 33.8%, 24.3% and 18.9% (high, mid, low);
  - 7B: 37.8%, 29.7% and 25.7%.
  - The overall finding is that mastering atomic skills does not guarantee high-level planning.
- The evaluation covers information-seeking and navigation tasks only; login, CAPTCHA and payment scenarios were excluded for privacy and security reasons.

*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

- [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) — Government body, Beijing, China · 246 works · 24,951 citations
- [Institute of Automation](https://md.research.elamur.ai/free/en/labs/institute-of-automation/) — Research institute, Beijing, China · 87 works · 14,883 citations
- [University of Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/universities/university-of-chinese-academy-of-sciences/) — University, Beijing, China · 188 works · 8,743 citations

📚 Shelves (3): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works

## Cite

Cite as: Tianyi Men, Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu and Jun Zhao. 2026. Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning. 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{men2026empowering,
  title = {{Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning}},
  author = {Tianyi Men, Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu and Jun Zhao},
  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.1670},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1670}
}
```

- [← previous Empathy in Diversity: Personalized Depression and Anxiety Therapy via Dialogue State Tracking and Patient-Aware Planning](https://md.research.elamur.ai/free/en/papers/yang-2026-empathy-diversity-personalized-depression-anxiety/)
- [next → Enabling Stroke-Level Structural Analysis of Hieroglyphic Scripts without Language-Specific Priors](https://md.research.elamur.ai/free/en/papers/luo-2026-enabling-stroke-level-structural-analysis/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/31/)

## References

50 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. John R Anderson. 2013. The architecture of cognition. Psychology Press. [find](https://scholar.google.com/scholar?q=John+R+Anderson%2E+2013%2E+The+architecture+of+cognition%2E+Psychology+Press%2E)
2. Anthropic. 2024. Introducing the next generation of claude. [find](https://scholar.google.com/scholar?q=Anthropic%2E+2024%2E+Introducing+the+next+generation+of+claude%2E)
3. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, and 1 others. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923. — [Qwen2.5-VL Technical Report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen2-5-vl-technical/)
4. Peter Belcak, Greg Heinrich, Shizhe Diao, Yonggan Fu, Xin Dong, Saurav Muralidharan, Yingyan Celine Lin, and Pavlo Molchanov. 2025. [Small language models are the future of agentic ai](https://md.research.elamur.ai/free/en/papers/belcak-2025-small-language-models-future-agentic/). arXiv preprint arXiv:2506.02153.
5. Yuxuan Cai, Yipeng Hao, Jie Zhou, Hang Yan, Zhikai Lei, Rui Zhen, Zhenhua Han, Yutao Yang, Junsong Li, Qianjun Pan, and 1 others. 2025. Building self-evolving agents via experience-driven lifelong learning: A framework and benchmark. arXiv preprint arXiv:2508.19005. — [arXiv:2508.19005](https://arxiv.org/abs/2508.19005) [find](https://scholar.google.com/scholar?q=Yuxuan+Cai%2C+Yipeng+Hao%2C+Jie+Zhou%2C+Hang+Yan%2C+Zhikai+Lei%2C+Rui+Zhen%2C+Zhenhua+Han%2C+Yutao+Yang%2C+Junsong+Li%2C+Qianjun+Pan%2C+and+1+others%2E+2025%2E+Building+self%2Devolving+agents+via+experience%2Ddriven+lifelong+lea)
6. Pengfei Cao, Tianyi Men, Wencan Liu, Jingwen Zhang, Xuzhao Li, Xixun Lin, Dianbo Sui, Yanan Cao, Kang Liu, and Jun Zhao. 2025. Large language models for planning: A comprehensive and systematic survey. arXiv preprint arXiv:2505.19683. — [arXiv:2505.19683](https://arxiv.org/abs/2505.19683) [find](https://scholar.google.com/scholar?q=Pengfei+Cao%2C+Tianyi+Men%2C+Wencan+Liu%2C+Jingwen+Zhang%2C+Xuzhao+Li%2C+Xixun+Lin%2C+Dianbo+Sui%2C+Yanan+Cao%2C+Kang+Liu%2C+and+Jun+Zhao%2E+2025%2E+Large+language+models+for+planning%3A+A+comprehensive+and+systematic+survey)
7. 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](https://md.research.elamur.ai/free/en/papers/deng-2023-mind2web-towards-generalist-agent-web/). In Thirty-seventh Conference on Neural Information Processing Systems.
8. Yue Fan, Handong Zhao, Ruiyi Zhang, Yu Shen, Xin Eric Wang, and Gang Wu. 2025. Gui-bee: Align gui action grounding to novel environments via autonomous exploration. arXiv preprint arXiv:2501.13896. [find](https://scholar.google.com/scholar?q=Yue+Fan%2C+Handong+Zhao%2C+Ruiyi+Zhang%2C+Yu+Shen%2C+Xin+Eric+Wang%2C+and+Gang+Wu%2E+2025%2E+Gui%2Dbee%3A+Align+gui+action+grounding+to+novel+environments+via+autonomous+exploration%2E+arXiv+preprint+arXiv%3A2501%2E13896%2E)
9. Runnan Fang, Yuan Liang, Xiaobin Wang, Jialong Wu, Shuofei Qiao, Pengjun Xie, Fei Huang, Huajun Chen, and Ningyu Zhang. 2025. Memp: Exploring agent procedural memory. arXiv preprint arXiv:2508.06433. [find](https://scholar.google.com/scholar?q=Runnan+Fang%2C+Yuan+Liang%2C+Xiaobin+Wang%2C+Jialong+Wu%2C+Shuofei+Qiao%2C+Pengjun+Xie%2C+Fei+Huang%2C+Huajun+Chen%2C+and+Ningyu+Zhang%2E+2025%2E+Memp%3A+Exploring+agent+procedural+memory%2E+arXiv+preprint+arXiv%3A2508%2E06433%2E)
10. Xinyu Geng, Peng Xia, Zhen Zhang, Xinyu Wang, Qiuchen Wang, Ruixue Ding, Chenxi Wang, Jialong Wu, Yida Zhao, Kuan Li, and 1 others. 2025. Webwatcher: Breaking new frontiers of vision-language deep research agent. arXiv preprint arXiv:2508.05748. — [arXiv:2508.05748](https://arxiv.org/abs/2508.05748) [find](https://scholar.google.com/scholar?q=Xinyu+Geng%2C+Peng+Xia%2C+Zhen+Zhang%2C+Xinyu+Wang%2C+Qiuchen+Wang%2C+Ruixue+Ding%2C+Chenxi+Wang%2C+Jialong+Wu%2C+Yida+Zhao%2C+Kuan+Li%2C+and+1+others%2E+2025%2E+Webwatcher%3A+Breaking+new+frontiers+of+vision%2Dlanguage+deep+res)
11. Yu Gu, Kai Zhang, Yuting Ning, Boyuan Zheng, Boyu Gou, Tianci Xue, Cheng Chang, Sanjari Srivastava, Yanan Xie, Peng Qi, and 1 others. 2024. Is your llm secretly a world model of the internet? model-based planning for web agents. arXiv preprint arXiv:2411.06559. — [arXiv:2411.06559](https://arxiv.org/abs/2411.06559) [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+and+1+others%2E+2024%2E+Is+your+llm+secretly+a+world+model+of+the+internet%3F+model%2Dba)
12. 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/). arXiv preprint arXiv:2401.13919.
13. Yuyang Hu, Shichun Liu, Yanwei Yue, Guibin Zhang, Boyang Liu, Fangyi Zhu, Jiahang Lin, Honglin Guo, Shihan Dou, Zhiheng Xi, and 1 others. 2025. Memory in the age of ai agents. arXiv preprint arXiv:2512.13564. — [arXiv:2512.13564](https://arxiv.org/abs/2512.13564) [find](https://scholar.google.com/scholar?q=Yuyang+Hu%2C+Shichun+Liu%2C+Yanwei+Yue%2C+Guibin+Zhang%2C+Boyang+Liu%2C+Fangyi+Zhu%2C+Jiahang+Lin%2C+Honglin+Guo%2C+Shihan+Dou%2C+Zhiheng+Xi%2C+and+1+others%2E+2025%2E+Memory+in+the+age+of+ai+agents%2E+arXiv+preprint+arXiv%3A251)
14. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, and 1 others. 2024. [Gpt-4o system card](https://md.research.elamur.ai/free/en/papers/openai-2024-gpt-4o-system-card/). arXiv preprint arXiv:2410.21276.
15. Zhuoran Jin, Hongbang Yuan, Tianyi Men, Pengfei Cao, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, and Jun Zhao. 2025. Rag-rewardbench: Benchmarking reward models in retrieval augmented generation for preference alignment. In Findings of the Association for Computational Linguistics: A… [find](https://scholar.google.com/scholar?q=Zhuoran+Jin%2C+Hongbang+Yuan%2C+Tianyi+Men%2C+Pengfei+Cao%2C+Yubo+Chen%2C+Jiexin+Xu%2C+Huaijun+Li%2C+Xiaojian+Jiang%2C+Kang+Liu%2C+and+Jun+Zhao%2E+2025%2E+Rag%2Drewardbench%3A+Benchmarking+reward+models+in+retrieval+augmented+)
16. Kuan Li, Zhongwang Zhang, Huifeng Yin, Liwen Zhang, Litu Ou, Jialong Wu, Wenbiao Yin, Baixuan Li, Zhengwei Tao, Xinyu Wang, and 1 others. 2025a. Websailor: Navigating super-human reasoning for web agent. arXiv preprint arXiv:2507.02592. [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+and+1+others%2E+2025a%2E+Websailor%3A+Navigating+super%2Dhuman+reasoning+for+web+age)
17. Tianle Li, Jihai Zhang, Yongming Rao, and Yu Cheng. 2025b. Unveiling the compositional ability gap in vision-language reasoning model. arXiv preprint arXiv:2505.19406. — [arXiv:2505.19406](https://arxiv.org/abs/2505.19406) [find](https://scholar.google.com/scholar?q=Tianle+Li%2C+Jihai+Zhang%2C+Yongming+Rao%2C+and+Yu+Cheng%2E+2025b%2E+Unveiling+the+compositional+ability+gap+in+vision%2Dlanguage+reasoning+model%2E+arXiv+preprint+arXiv%3A2505%2E19406%2E+%E2%80%94+%5BarXiv%3A2505%2E19406%5D%28https%3A%2F%2Farx)
18. Yangning Li, Weizhi Zhang, Yuyao Yang, Wei-Chieh Huang, Yaozu Wu, Junyu Luo, Yuanchen Bei, Henry Peng Zou, Xiao Luo, Yusheng Zhao, and 1 others. 2025c. [Towards agentic rag with deep reasoning: A survey of rag-reasoning systems in llms](https://md.research.elamur.ai/free/en/papers/li-2025-towards-agentic-rag-deep-reasoning/). arXiv preprint arXiv:2507.09477.
19. Yunxin Li, Zhenyu Liu, Zitao Li, Xuanyu Zhang, Zhenran Xu, Xinyu Chen, Haoyuan Shi, Shenyuan Jiang, Xintong Wang, Jifang Wang, and 1 others. 2025d. Perception, reason, think, and plan: A survey on large multimodal reasoning models. arXiv preprint arXiv:2505.04921. — [arXiv:2505.04921](https://arxiv.org/abs/2505.04921) [find](https://scholar.google.com/scholar?q=Yunxin+Li%2C+Zhenyu+Liu%2C+Zitao+Li%2C+Xuanyu+Zhang%2C+Zhenran+Xu%2C+Xinyu+Chen%2C+Haoyuan+Shi%2C+Shenyuan+Jiang%2C+Xintong+Wang%2C+Jifang+Wang%2C+and+1+others%2E+2025d%2E+Perception%2C+reason%2C+think%2C+and+plan%3A+A+survey+on+lar)
20. Haojia Lin, Xiaoyu Tan, Yulei Qin, Zihan Xu, Yuchen Shi, Zongyi Li, Gang Li, Shaofei Cai, Siqi Cai, Chaoyou Fu, and 1 others. 2025. Cuareward-bench: A benchmark for evaluating reward models on computer-using agent. arXiv preprint arXiv:2510.18596. — [arXiv:2510.18596](https://arxiv.org/abs/2510.18596) [find](https://scholar.google.com/scholar?q=Haojia+Lin%2C+Xiaoyu+Tan%2C+Yulei+Qin%2C+Zihan+Xu%2C+Yuchen+Shi%2C+Zongyi+Li%2C+Gang+Li%2C+Shaofei+Cai%2C+Siqi+Cai%2C+Chaoyou+Fu%2C+and+1+others%2E+2025%2E+Cuareward%2Dbench%3A+A+benchmark+for+evaluating+reward+models+on+compute)
21. Lajanugen Logeswaran, Jaekyeom Kim, Sungryull Sohn, Creighton Glasscock, and Honglak Lee. 2025. Scaling web agent training through automatic data generation and fine-grained evaluation. In Second Conference on Language Modeling. [find](https://scholar.google.com/scholar?q=Lajanugen+Logeswaran%2C+Jaekyeom+Kim%2C+Sungryull+Sohn%2C+Creighton+Glasscock%2C+and+Honglak+Lee%2E+2025%2E+Scaling+web+agent+training+through+automatic+data+generation+and+fine%2Dgrained+evaluation%2E+In+Second+Conf)
22. Zhengxi Lu, Yuxiang Chai, Yaxuan Guo, Xi Yin, Liang Liu, Hao Wang, Han Xiao, Shuai Ren, Guanjing Xiong, and Hongsheng Li. 2025. Ui-r1: Enhancing efficient action prediction of gui agents by reinforcement learning. arXiv preprint arXiv:2503.21620. — [arXiv:2503.21620](https://arxiv.org/abs/2503.21620) [find](https://scholar.google.com/scholar?q=Zhengxi+Lu%2C+Yuxiang+Chai%2C+Yaxuan+Guo%2C+Xi+Yin%2C+Liang+Liu%2C+Hao+Wang%2C+Han+Xiao%2C+Shuai+Ren%2C+Guanjing+Xiong%2C+and+Hongsheng+Li%2E+2025%2E+Ui%2Dr1%3A+Enhancing+efficient+action+prediction+of+gui+agents+by+reinforcem)
23. Run Luo, Lu Wang, Wanwei He, and Xiaobo Xia. 2025. Gui-r1: A generalist r1-style vision-language action model for gui agents. arXiv preprint arXiv:2504.10458. — [arXiv:2504.10458](https://arxiv.org/abs/2504.10458) [find](https://scholar.google.com/scholar?q=Run+Luo%2C+Lu+Wang%2C+Wanwei+He%2C+and+Xiaobo+Xia%2E+2025%2E+Gui%2Dr1%3A+A+generalist+r1%2Dstyle+vision%2Dlanguage+action+model+for+gui+agents%2E+arXiv+preprint+arXiv%3A2504%2E10458%2E+%E2%80%94+%5BarXiv%3A2504%2E10458%5D%28https%3A%2F%2Farxiv%2Eorg%2Fab)
24. Tianyi Men, Pengfei Cao, Zhuoran Jin, Yubo Chen, Kang Liu, and Jun Zhao. 2024. Unlocking the future: Exploring look-ahead planning mechanistic interpretability in large language models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 7713–7724. [find](https://scholar.google.com/scholar?q=Tianyi+Men%2C+Pengfei+Cao%2C+Zhuoran+Jin%2C+Yubo+Chen%2C+Kang+Liu%2C+and+Jun+Zhao%2E+2024%2E+Unlocking+the+future%3A+Exploring+look%2Dahead+planning+mechanistic+interpretability+in+large+language+models%2E+In+Proceedings)
25. Tianyi Men, Pengfei Cao, Zhuoran Jin, Yubo Chen, Kang Liu, and Jun Zhao. 2025a. A troublemaker with contagious jailbreak makes chaos in honest towns. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 17561–17587. [find](https://scholar.google.com/scholar?q=Tianyi+Men%2C+Pengfei+Cao%2C+Zhuoran+Jin%2C+Yubo+Chen%2C+Kang+Liu%2C+and+Jun+Zhao%2E+2025a%2E+A+troublemaker+with+contagious+jailbreak+makes+chaos+in+honest+towns%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+A)
26. Tianyi Men, Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu, and Jun Zhao. 2025b. Agent-rewardbench: Towards a unified benchmark for reward modeling across perception, planning, and safety in real-world multimodal agents. In Proceedings of the 63rd Annual Meeting of the Association for Computational L… [find](https://scholar.google.com/scholar?q=Tianyi+Men%2C+Zhuoran+Jin%2C+Pengfei+Cao%2C+Yubo+Chen%2C+Kang+Liu%2C+and+Jun+Zhao%2E+2025b%2E+Agent%2Drewardbench%3A+Towards+a+unified+benchmark+for+reward+modeling+across+perception%2C+planning%2C+and+safety+in+real%2Dworld)
27. Dang Nguyen, Jian Chen, Yu Wang, Gang Wu, Namyong Park, Zhengmian Hu, Hanjia Lyu, Junda Wu, Ryan Aponte, Yu Xia, and 1 others. 2025. Gui agents: A survey. In Findings of the Association for Computational Linguistics: ACL 2025, pages 22522–22538. [find](https://scholar.google.com/scholar?q=Dang+Nguyen%2C+Jian+Chen%2C+Yu+Wang%2C+Gang+Wu%2C+Namyong+Park%2C+Zhengmian+Hu%2C+Hanjia+Lyu%2C+Junda+Wu%2C+Ryan+Aponte%2C+Yu+Xia%2C+and+1+others%2E+2025%2E+Gui+agents%3A+A+survey%2E+In+Findings+of+the+Association+for+Computatio)
28. Liangbo Ning, Ziran Liang, Zhuohang Jiang, Haohao Qu, Yujuan Ding, Wenqi Fan, Xiao-yong Wei, Shanru Lin, Hui Liu, Philip S Yu, and 1 others. 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](https://scholar.google.com/scholar?q=Liangbo+Ning%2C+Ziran+Liang%2C+Zhuohang+Jiang%2C+Haohao+Qu%2C+Yujuan+Ding%2C+Wenqi+Fan%2C+Xiao%2Dyong+Wei%2C+Shanru+Lin%2C+Hui+Liu%2C+Philip+S+Yu%2C+and+1+others%2E+2025%2E+A+survey+of+webagents%3A+Towards+next%2Dgeneration+ai+age)
29. Nils Reimers and Iryna Gurevych. 2020. [Making monolingual sentence embeddings multilingual using knowledge distillation](https://md.research.elamur.ai/free/en/papers/reimers-2020-making-monolingual-sentence-embeddings-multilingual/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.
30. Brian H Ross. 1989. Some psychological results on case-based reasoning. In Proceedings: Case-based reasoning workshop, pages 144–147. Morgan Kaufmann. [find](https://scholar.google.com/scholar?q=Brian+H+Ross%2E+1989%2E+Some+psychological+results+on+case%2Dbased+reasoning%2E+In+Proceedings%3A+Case%2Dbased+reasoning+workshop%2C+pages+144%E2%80%93147%2E+Morgan+Kaufmann%2E)
31. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Yang Wu, and 1 others. 2024. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). arXiv preprint arXiv:2402.03300.
32. David Silver and Richard S Sutton. 2025. Welcome to the era of experience. Google AI, 1. [find](https://scholar.google.com/scholar?q=David+Silver+and+Richard+S+Sutton%2E+2025%2E+Welcome+to+the+era+of+experience%2E+Google+AI%2C+1%2E)
33. Hongjin Su, Ruoxi Sun, Jinsung Yoon, Pengcheng Yin, Tao Yu, and Sercan Ö Arık. 2025. Learn-by-interact: A data-centric framework for self-adaptive agents in realistic environments. arXiv preprint arXiv:2501.10893. — [arXiv:2501.10893](https://arxiv.org/abs/2501.10893) [find](https://scholar.google.com/scholar?q=Hongjin+Su%2C+Ruoxi+Sun%2C+Jinsung+Yoon%2C+Pengcheng+Yin%2C+Tao+Yu%2C+and+Sercan+%C3%96+Ar%C4%B1k%2E+2025%2E+Learn%2Dby%2Dinteract%3A+A+data%2Dcentric+framework+for+self%2Dadaptive+agents+in+realistic+environments%2E+arXiv+preprint+arXi)
34. Qiushi Sun, Kanzhi Cheng, Zichen Ding, Chuanyang Jin, Yian Wang, Fangzhi Xu, Zhenyu Wu, Chengyou Jia, Liheng Chen, Zhoumianze Liu, and 1 others. 2025. [Os-genesis: Automating gui agent trajectory construction via reverse task synthesis](https://md.research.elamur.ai/free/en/papers/sun-2025-os-genesis-automating-gui-agent/). In Proceedings of the 63rd Annual Meeting of the Association for…
35. Fei Tang, Haolei Xu, Hang Zhang, Siqi Chen, Xingyu Wu, Yongliang Shen, Wenqi Zhang, Guiyang Hou, Zeqi Tan, Yuchen Yan, and 1 others. 2025a. A survey on (m) llm-based gui agents. arXiv preprint arXiv:2504.13865. — [arXiv:2504.13865](https://arxiv.org/abs/2504.13865) [find](https://scholar.google.com/scholar?q=Fei+Tang%2C+Haolei+Xu%2C+Hang+Zhang%2C+Siqi+Chen%2C+Xingyu+Wu%2C+Yongliang+Shen%2C+Wenqi+Zhang%2C+Guiyang+Hou%2C+Zeqi+Tan%2C+Yuchen+Yan%2C+and+1+others%2E+2025a%2E+A+survey+on+%28m%29+llm%2Dbased+gui+agents%2E+arXiv+preprint+arXiv%3A2)
36. Xiangru Tang, Tianrui Qin, Tianhao Peng, Ziyang Zhou, Daniel Shao, Tingting Du, Xinming Wei, Peng Xia, Fang Wu, He Zhu, and 1 others. 2025b. Agent kb: Leveraging cross-domain experience for agentic problem solving. arXiv preprint arXiv:2507.06229. — [arXiv:2507.06229](https://arxiv.org/abs/2507.06229) [find](https://scholar.google.com/scholar?q=Xiangru+Tang%2C+Tianrui+Qin%2C+Tianhao+Peng%2C+Ziyang+Zhou%2C+Daniel+Shao%2C+Tingting+Du%2C+Xinming+Wei%2C+Peng+Xia%2C+Fang+Wu%2C+He+Zhu%2C+and+1+others%2E+2025b%2E+Agent+kb%3A+Leveraging+cross%2Ddomain+experience+for+agentic+pr)
37. Huichi Zhou, Yihang Chen, Siyuan Guo, Xue Yan, Kin Hei Lee, Zihan Wang, Ka Yiu Lee, Guchun Zhang, Kun Shao, Linyi Yang, and 1 others. 2025a. Memento: Fine-tuning llm agents without fine-tuning llms. Preprint. [find](https://scholar.google.com/scholar?q=Huichi+Zhou%2C+Yihang+Chen%2C+Siyuan+Guo%2C+Xue+Yan%2C+Kin+Hei+Lee%2C+Zihan+Wang%2C+Ka+Yiu+Lee%2C+Guchun+Zhang%2C+Kun+Shao%2C+Linyi+Yang%2C+and+1+others%2E+2025a%2E+Memento%3A+Fine%2Dtuning+llm+agents+without+fine%2Dtuning+llms%2E+P)
38. Zhengwei Tao, Jialong Wu, Wenbiao Yin, Junkai Zhang, Baixuan Li, Haiyang Shen, Kuan Li, Liwen Zhang, Xinyu Wang, Yong Jiang, and 1 others. 2025. Webshaper: Agentically data synthesizing via information-seeking formalization. arXiv 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+and+1+others%2E+2025%2E+Webshaper%3A+Agentically+data+synthesizing+via+informatio)
39. Yifei Zhou, Qianlan Yang, Kaixiang Lin, Min Bai, Xiong Zhou, Yu-Xiong Wang, Sergey Levine, and Li Erran Li. 2025b. Proposer-agent-evaluator (pae): Autonomous skill discovery for foundation model internet agents. In Forty-second International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Yifei+Zhou%2C+Qianlan+Yang%2C+Kaixiang+Lin%2C+Min+Bai%2C+Xiong+Zhou%2C+Yu%2DXiong+Wang%2C+Sergey+Levine%2C+and+Li+Erran+Li%2E+2025b%2E+Proposer%2Dagent%2Devaluator+%28pae%29%3A+Autonomous+skill+discovery+for+foundation+model+inter)
40. Brandon Trabucco, Gunnar Sigurdsson, Robinson Piramuthu, and Ruslan Salakhutdinov. 2025. Insta: Towards internet-scale training for agents. arXiv preprint arXiv:2502.06776. [find](https://scholar.google.com/scholar?q=Brandon+Trabucco%2C+Gunnar+Sigurdsson%2C+Robinson+Piramuthu%2C+and+Ruslan+Salakhutdinov%2E+2025%2E+Insta%3A+Towards+internet%2Dscale+training+for+agents%2E+arXiv+preprint+arXiv%3A2502%2E06776%2E)
41. Yuqi Zhou, Sunhao Dai, Shuai Wang, Kaiwen Zhou, Qinglin Jia, and Jun Xu. 2025c. Gui-g1: Understanding r1-zero-like training for visual grounding in gui agents, 2025. URL https://arxiv.org/abs/2505.15810, 3:36–37. — [arXiv:2505.15810](https://arxiv.org/abs/2505.15810) [↗](https://arxiv.org/abs/2505.15810)
42. Shuai Wang, Weiwen Liu, Jingxuan Chen, Yuqi Zhou, Weinan Gan, Xingshan Zeng, Yuhan Che, Shuai Yu, Xinlong Hao, Kun Shao, and 1 others. 2024a. Gui agents with foundation models: A comprehensive survey. arXiv preprint arXiv:2411.04890. — [arXiv:2411.04890](https://arxiv.org/abs/2411.04890) [find](https://scholar.google.com/scholar?q=Shuai+Wang%2C+Weiwen+Liu%2C+Jingxuan+Chen%2C+Yuqi+Zhou%2C+Weinan+Gan%2C+Xingshan+Zeng%2C+Yuhan+Che%2C+Shuai+Yu%2C+Xinlong+Hao%2C+Kun+Shao%2C+and+1+others%2E+2024a%2E+Gui+agents+with+foundation+models%3A+A+comprehensive+survey%2E)
43. Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, and Graham Neubig. 2024b. [Agent workflow memory](https://md.research.elamur.ai/free/en/papers/wang-2024-agent-workflow-memory/). arXiv preprint arXiv:2409.07429.
44. Hui Wei, Zihao Zhang, Shenghua He, Tian Xia, Shijia Pan, and Fei Liu. 2025. [Plangenllms: A modern survey of llm planning capabilities](https://md.research.elamur.ai/free/en/papers/wei-2025-plangenllms-modern-survey-llm-planning/). arXiv preprint arXiv:2502.11221.
45. Peng Xia, Jianwen Chen, Hanyang Wang, Jiaqi Liu, Kaide Zeng, Yu Wang, Siwei Han, Yiyang Zhou, Xujiang Zhao, Haifeng Chen, and 1 others. 2026. Skillrl: Evolving agents via recursive skill-augmented reinforcement learning. arXiv preprint arXiv:2602.08234. — [arXiv:2602.08234](https://arxiv.org/abs/2602.08234) [find](https://scholar.google.com/scholar?q=Peng+Xia%2C+Jianwen+Chen%2C+Hanyang+Wang%2C+Jiaqi+Liu%2C+Kaide+Zeng%2C+Yu+Wang%2C+Siwei+Han%2C+Yiyang+Zhou%2C+Xujiang+Zhao%2C+Haifeng+Chen%2C+and+1+others%2E+2026%2E+Skillrl%3A+Evolving+agents+via+recursive+skill%2Daugmented+rei)
46. 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).
47. Shenzhi Wang Zhangchi Feng Dongdong Kuang Yuwen Xiong Yaowei Zheng, Junting Lu. 2025. Easyr1: An efficient, scalable, multi-modality rl training framework. [find](https://scholar.google.com/scholar?q=Shenzhi+Wang+Zhangchi+Feng+Dongdong+Kuang+Yuwen+Xiong+Yaowei+Zheng%2C+Junting+Lu%2E+2025%2E+Easyr1%3A+An+efficient%2C+scalable%2C+multi%2Dmodality+rl+training+framework%2E)
48. Weizhi Zhang, Yangning Li, Yuanchen Bei, Junyu Luo, Guancheng Wan, Liangwei Yang, Chenxuan Xie, Yuyao Yang, Wei-Chieh Huang, Chunyu Miao, and 1 others. 2025. From web search towards agentic deep research: Incentivizing search with reasoning agents. arXiv preprint arXiv:2506.18959. — [arXiv:2506.18959](https://arxiv.org/abs/2506.18959) [find](https://scholar.google.com/scholar?q=Weizhi+Zhang%2C+Yangning+Li%2C+Yuanchen+Bei%2C+Junyu+Luo%2C+Guancheng+Wan%2C+Liangwei+Yang%2C+Chenxuan+Xie%2C+Yuyao+Yang%2C+Wei%2DChieh+Huang%2C+Chunyu+Miao%2C+and+1+others%2E+2025%2E+From+web+search+towards+agentic+deep+resea)
49. Boyuan Zheng, Boyu Gou, Jihyung Kil, Huan Sun, and Yu Su. 2024a. [Gpt-4v(ision) is a generalist web agent, if grounded](https://md.research.elamur.ai/free/en/papers/zheng-2024-gpt-4v-ision-generalist-web/).
50. Yaowei Zheng, Richong Zhang, Junhao Zhang, Yanhan Ye, Zheyan Luo, Zhangchi Feng, and Yongqiang Ma. 2024b. [Llamafactory: Unified efficient fine-tuning of 100+ language models](https://md.research.elamur.ai/free/en/papers/zheng-2024-llamafactory-unified-efficient-fine-tuning/). arXiv preprint arXiv:2403.13372.

*Updated 2 November 2026*