---
title: "UI-TARS-2 Technical Report — paper by Wang et al. (2025)"
description: "The authors build four components to address them: a data flywheel in which model and data improve… 88 references, cited by 26 papers here."
authors: ["Haoming Wang", "Haoyang Zou", "Huatong Song", "Jiazhan Feng", "Junjie Fang", "Junting Lu", "Longxiang Liu", "Qinyu Luo", "Shihao Liang", "Shijue Huang", "Wanjun Zhong", "Yining Ye", "Yujia Qin", "Yuwen Xiong", "Yuxin Song", "Zhiyong Wu", "Aoyan Li", "Bo Li", "Chen Dun", "Chong Liu", "Daoguang Zan", "Fuxing Leng", "Hanbin Wang", "Hao Yu", "Haobin Chen", "Hongyi Guo", "Jing Su", "Jingjia Huang", "Kai Shen", "Kaiyu Shi", "Lin Yan", "Peiyao Zhao", "Pengfei Liu", "Qinghao Ye", "Renjie Zheng", "Shulin Xin", "Wayne Xin Zhao", "Wen Heng", "Wenhao Huang", "Wenqian Wang", "Xiaobo Qin", "Yi Lin", "Youbin Wu", "Zehui Chen", "Zihao Wang", "Baoquan Zhong", "Xinchun Zhang", "Xujing Li", "Yuanfan Li", "Zhongkai Zhao", "Chengquan Jiang", "Faming Wu", "Haotian Zhou", "Jinlin Pang", "Li Han", "Qi Liu", "Qianli Ma", "Siyao Liu", "Songhua Cai", "Wenqi Fu", "Xin Liu", "Yaohui Wang", "Zhi Zhang", "Bo Zhou", "Guoliang Li", "Jiajun Shi", "Jiale Yang", "Jie Tang", "Li Li", "Qihua Han", "Taoran Lu", "Woyu Lin", "Xiaokang Tong", "Xinyao Li", "Yichi Zhang", "Yu Miao", "Zhengxuan Jiang", "Zili Li", "Ziyuan Zhao", "Chenxin Li", "Dehua Ma", "Feng Lin", "Ge Zhang", "Haihua Yang", "Hangyu Guo", "Hongda Zhu", "Jiaheng Liu", "Junda Du", "Kai Cai", "Kuanye Li", "Lichen Yuan", "Meilan Han", "Minchao Wang", "Shuyue Guo", "Tianhao Cheng", "Xiaobo Ma", "Xiaojun Xiao", "Xiaolong Huang", "Xinjie Chen", "Yidi Du", "Yilin Chen", "Yiwen Wang", "Zhaojian Li", "Zhenzhu Yang", "Zhiyuan Zeng", "Chaolin Jin", "Chen Li", "Hao Chen", "Haoli Chen", "Jian Chen", "Qinghao Zhao", "Guang Shi"]
year: 2025
venue: "arXiv:2509.02544"
source: "https://arxiv.org/abs/2509.02544"
doi: "10.48550/arxiv.2509.02544"
arxiv: "2509.02544"
licence: "arXiv — non-exclusive licence to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wang-2025-ui-tars-2-technical/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2025-ui-tars-2-technical/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/4/) / UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

# UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

**Authors:** [Haoming Wang](https://md.research.elamur.ai/free/en/authors/haoming-wang/), Haoyang Zou, [Huatong Song](https://md.research.elamur.ai/free/en/authors/huatong-song/), [Jiazhan Feng](https://md.research.elamur.ai/free/en/authors/jiazhan-feng/), [Junjie Fang](https://md.research.elamur.ai/free/en/authors/junjie-fang/), Junting Lu, Longxiang Liu, [Qinyu Luo](https://md.research.elamur.ai/free/en/authors/qinyu-luo/), [Shihao Liang](https://md.research.elamur.ai/free/en/authors/shihao-liang/), [Shijue Huang](https://md.research.elamur.ai/free/en/authors/shijue-huang/), [Wanjun Zhong](https://md.research.elamur.ai/free/en/authors/wanjun-zhong/), [Yining Ye](https://md.research.elamur.ai/free/en/authors/yining-ye/), [Yujia Qin](https://md.research.elamur.ai/free/en/authors/yujia-qin/), Yuwen Xiong, Yuxin Song, [Zhiyong Wu](https://md.research.elamur.ai/free/en/authors/zhiyong-wu/), Aoyan Li, [Bo Li](https://md.research.elamur.ai/free/en/authors/bo-li/), Chen Dun, [Chong Liu](https://md.research.elamur.ai/free/en/authors/chong-liu/), [Daoguang Zan](https://md.research.elamur.ai/free/en/authors/daoguang-zan/), Fuxing Leng, [Hanbin Wang](https://md.research.elamur.ai/free/en/authors/hanbin-wang/), [Hao Yu](https://md.research.elamur.ai/free/en/authors/hao-yu/), Haobin Chen, Hongyi Guo, [Jing Su](https://md.research.elamur.ai/free/en/authors/jing-su/), Jingjia Huang, Kai Shen, Kaiyu Shi, Lin Yan, Peiyao Zhao, [Pengfei Liu](https://md.research.elamur.ai/free/en/authors/pengfei-liu/), [Qinghao Ye](https://md.research.elamur.ai/free/en/authors/qinghao-ye/), [Renjie Zheng](https://md.research.elamur.ai/free/en/authors/renjie-zheng/), Shulin Xin, [Wayne Xin Zhao](https://md.research.elamur.ai/free/en/authors/wayne-xin-zhao/), Wen Heng, [Wenhao Huang](https://md.research.elamur.ai/free/en/authors/wenhao-huang/), Wenqian Wang, Xiaobo Qin, Yi Lin, Youbin Wu, [Zehui Chen](https://md.research.elamur.ai/free/en/authors/zehui-chen/), [Zihao Wang](https://md.research.elamur.ai/free/en/authors/zihao-wang/), Baoquan Zhong, Xinchun Zhang, Xujing Li, Yuanfan Li, Zhongkai Zhao, Chengquan Jiang, Faming Wu, Haotian Zhou, Jinlin Pang, Li Han, [Qi Liu](https://md.research.elamur.ai/free/en/authors/qi-liu/), [Qianli Ma](https://md.research.elamur.ai/free/en/authors/qianli-ma/), Siyao Liu, Songhua Cai, Wenqi Fu, [Xin Liu](https://md.research.elamur.ai/free/en/authors/xin-liu/), Yaohui Wang, Zhi Zhang, Bo Zhou, Guoliang Li, [Jiajun Shi](https://md.research.elamur.ai/free/en/authors/jiajun-shi/), Jiale Yang, [Jie Tang](https://md.research.elamur.ai/free/en/authors/jie-tang/), [Li Li](https://md.research.elamur.ai/free/en/authors/li-li/), Qihua Han, Taoran Lu, Woyu Lin, Xiaokang Tong, Xinyao Li, [Yichi Zhang](https://md.research.elamur.ai/free/en/authors/yichi-zhang/), Yu Miao, Zhengxuan Jiang, Zili Li, Ziyuan Zhao, Chenxin Li, Dehua Ma, Feng Lin, [Ge Zhang](https://md.research.elamur.ai/free/en/authors/ge-zhang/), [Haihua Yang](https://md.research.elamur.ai/free/en/authors/haihua-yang/), [Hangyu Guo](https://md.research.elamur.ai/free/en/authors/hangyu-guo/), Hongda Zhu, [Jiaheng Liu](https://md.research.elamur.ai/free/en/authors/jiaheng-liu/), Junda Du, Kai Cai, Kuanye Li, Lichen Yuan, Meilan Han, Minchao Wang, [Shuyue Guo](https://md.research.elamur.ai/free/en/authors/shuyue-guo/), [Tianhao Cheng](https://md.research.elamur.ai/free/en/authors/tianhao-cheng/), Xiaobo Ma, Xiaojun Xiao, [Xiaolong Huang](https://md.research.elamur.ai/free/en/authors/xiaolong-huang/), Xinjie Chen, Yidi Du, Yilin Chen, Yiwen Wang, Zhaojian Li, Zhenzhu Yang, [Zhiyuan Zeng](https://md.research.elamur.ai/free/en/authors/zhiyuan-zeng/), Chaolin Jin, [Chen Li](https://md.research.elamur.ai/free/en/authors/chen-li/), [Hao Chen](https://md.research.elamur.ai/free/en/authors/hao-chen/), Haoli Chen, [Jian Chen](https://md.research.elamur.ai/free/en/authors/jian-chen/), Qinghao Zhao and Guang Shi · **Year:** 2025 · **Venue:** arXiv:2509.02544 · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2509.02544) · [PDF](https://arxiv.org/pdf/2509.02544) · [DOI 10.48550/arxiv.2509.02544](https://doi.org/10.48550/arxiv.2509.02544) · [arXiv 2509.02544](https://arxiv.org/abs/2509.02544) · [OpenAlex](https://openalex.org/W4414757783)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [26](https://md.research.elamur.ai/free/en/papers/wang-2025-ui-tars-2-technical/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
UI-TARS-2 (ByteDance Seed) is a native GUI agent: a single end-to-end policy that perceives, reasons, remembers and acts across desktops, phones, browsers and games. The report tackles four obstacles: expensive long-horizon trajectory data, unstable multi-turn RL with sparse rewards, the limits of pure mouse-and-keyboard control, and fragile large-scale environments. The authors build four components to address them:

- a data flywheel in which model and data improve together through continual pre-training, SFT, rejection sampling and RL;
- a PPO-based RL framework with asynchronous stateful rollouts and streaming updates, plus shaped rewards, an adaptive approach to estimating advantages, and pretraining of the value model;
- a hybrid environment that exposes terminals, file systems and MCP tools via GUI-SDK;
- a unified sandbox that runs millions of rollouts.

Specialized vertical agents are then merged by parameter interpolation. The resulting model clearly surpasses UI-TARS-1.5, often beats Claude and OpenAI agents, and transfers to web search and coding. Its analyses of training dynamics also give practical guidance for running agent RL stably at scale.

## Key points
- GUI benchmark scores: Online-Mind2Web 88.2, OSWorld 47.5, WindowsAgentArena 50.6, AndroidWorld 73.3.
- Games: a mean normalized score of 59.8 on a 15-game suite, about three-fifths of human level. This is 2.4× OpenAI CUA and 2.8× Claude Computer Use. The model is also competitive with OpenAI o3 on LMGame-Bench.
- With GUI-SDK extensions, the model reaches BrowseComp 29.6, Terminal Bench 45.3 and SWE-Bench Verified 68.7.
- The agent follows the ReAct loop (reasoning, action, observation). Its hierarchical memory pairs a detailed Working Memory with a compressed Episodic Memory.
- Code and a desktop app are available at github.com/bytedance/ui-tars and UI-TARS-desktop.

*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 (2): [🖥️ 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

## Cite

Cite as: Haoming Wang, Haoyang Zou, Huatong Song, Jiazhan Feng, Junjie Fang, Junting Lu, Longxiang Liu, Qinyu Luo, Shihao Liang, Shijue Huang, Wanjun Zhong, Yining Ye, Yujia Qin, Yuwen Xiong, Yuxin Song, Zhiyong Wu, Aoyan Li, Bo Li, Chen Dun, Chong Liu, Daoguang Zan, Fuxing Leng, Hanbin Wang, Hao Yu, Haobin Chen, Hongyi Guo, Jing Su, Jingjia Huang, Kai Shen, Kaiyu Shi, Lin Yan, Peiyao Zhao, Pengfei Liu, Qinghao Ye, Renjie Zheng, Shulin Xin, Wayne Xin Zhao, Wen Heng, Wenhao Huang, Wenqian Wang, Xiaobo Qin, Yi Lin, Youbin Wu, Zehui Chen, Zihao Wang, Baoquan Zhong, Xinchun Zhang, Xujing Li, Yuanfan Li, Zhongkai Zhao, Chengquan Jiang, Faming Wu, Haotian Zhou, Jinlin Pang, Li Han, Qi Liu, Qianli Ma, Siyao Liu, Songhua Cai, Wenqi Fu, Xin Liu, Yaohui Wang, Zhi Zhang, Bo Zhou, Guoliang Li, Jiajun Shi, Jiale Yang, Jie Tang, Li Li, Qihua Han, Taoran Lu, Woyu Lin, Xiaokang Tong, Xinyao Li, Yichi Zhang, Yu Miao, Zhengxuan Jiang, Zili Li, Ziyuan Zhao, Chenxin Li, Dehua Ma, Feng Lin, Ge Zhang, Haihua Yang, Hangyu Guo, Hongda Zhu, Jiaheng Liu, Junda Du, Kai Cai, Kuanye Li, Lichen Yuan, Meilan Han, Minchao Wang, Shuyue Guo, Tianhao Cheng, Xiaobo Ma, Xiaojun Xiao, Xiaolong Huang, Xinjie Chen, Yidi Du, Yilin Chen, Yiwen Wang, Zhaojian Li, Zhenzhu Yang, Zhiyuan Zeng, Chaolin Jin, Chen Li, Hao Chen, Haoli Chen, Jian Chen, Qinghao Zhao and Guang Shi. 2025. UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning. arXiv:2509.02544.

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

```bibtex
@misc{wang2025ui,
  title = {{UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning}},
  author = {Haoming Wang, Haoyang Zou, Huatong Song, Jiazhan Feng, Junjie Fang, Junting Lu, Longxiang Liu, Qinyu Luo, Shihao Liang, Shijue Huang, Wanjun Zhong, Yining Ye, Yujia Qin, Yuwen Xiong, Yuxin Song, Zhiyong Wu, Aoyan Li, Bo Li, Chen Dun, Chong Liu, Daoguang Zan, Fuxing Leng, Hanbin Wang, Hao Yu, Haobin Chen, Hongyi Guo, Jing Su, Jingjia Huang, Kai Shen, Kaiyu Shi, Lin Yan, Peiyao Zhao, Pengfei Liu, Qinghao Ye, Renjie Zheng, Shulin Xin, Wayne Xin Zhao, Wen Heng, Wenhao Huang, Wenqian Wang, Xiaobo Qin, Yi Lin, Youbin Wu, Zehui Chen, Zihao Wang, Baoquan Zhong, Xinchun Zhang, Xujing Li, Yuanfan Li, Zhongkai Zhao, Chengquan Jiang, Faming Wu, Haotian Zhou, Jinlin Pang, Li Han, Qi Liu, Qianli Ma, Siyao Liu, Songhua Cai, Wenqi Fu, Xin Liu, Yaohui Wang, Zhi Zhang, Bo Zhou, Guoliang Li, Jiajun Shi, Jiale Yang, Jie Tang, Li Li, Qihua Han, Taoran Lu, Woyu Lin, Xiaokang Tong, Xinyao Li, Yichi Zhang, Yu Miao, Zhengxuan Jiang, Zili Li, Ziyuan Zhao, Chenxin Li, Dehua Ma, Feng Lin, Ge Zhang, Haihua Yang, Hangyu Guo, Hongda Zhu, Jiaheng Liu, Junda Du, Kai Cai, Kuanye Li, Lichen Yuan, Meilan Han, Minchao Wang, Shuyue Guo, Tianhao Cheng, Xiaobo Ma, Xiaojun Xiao, Xiaolong Huang, Xinjie Chen, Yidi Du, Yilin Chen, Yiwen Wang, Zhaojian Li, Zhenzhu Yang, Zhiyuan Zeng, Chaolin Jin, Chen Li, Hao Chen, Haoli Chen, Jian Chen, Qinghao Zhao and Guang Shi},
  year = {2025},
  doi = {10.48550/arxiv.2509.02544},
  eprint = {2509.02544},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2509.02544}
}
```

- [← previous TreeRL: LLM Reinforcement Learning with On-Policy Tree Search](https://md.research.elamur.ai/free/en/papers/hou-2025-treerl-llm-reinforcement-learning-policy/)
- [next → Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models](https://md.research.elamur.ai/free/en/papers/zhifei-2025-audio-reasoner-improving-reasoning-capability/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/4/)

## References

88 references, 24 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Anthropic. Introducing the model context protocol, 2024. model-context-protocol. [find](https://scholar.google.com/scholar?q=Anthropic%2E+Introducing+the+model+context+protocol%2C+2024%2E+model%2Dcontext%2Dprotocol%2E)
2. Anthropic. Developing a computer use model. [https://www.anthropic.com/news/developing-computer-use](https://www.anthropic.com/news/developing-computer-use), 2024. Product announcement. [↗](https://www.anthropic.com/news/developing-computer-use)
3. Anthropic. Claude 3.7 sonnet system card. 2025. Claude’s extended [find](https://scholar.google.com/scholar?q=Anthropic%2E+Claude+3%2E7+sonnet+system+card%2E+2025%2E+Claude%E2%80%99s+extended)
4. anthropic. Introducing claude 4, 2025. URL [https://www.anthropic.com/news/claude-4](https://www.anthropic.com/news/claude-4). [↗](https://www.anthropic.com/news/claude-4)
5. Ibragim Badertdinov, Maria Trofimova, Yury Anapolskiy, Sergey Abramov, Karina Zainullina, Alexander Golubev, Sergey Polezhaev, Daria Litvintseva, Simon Karasik, Filipp Fisin, Sergey Skvortsov, Maxim Nekrashevich, Anton Shevtsov, and Boris Yangel. Scaling data collection for training software enginee… [find](https://scholar.google.com/scholar?q=Ibragim+Badertdinov%2C+Maria+Trofimova%2C+Yury+Anapolskiy%2C+Sergey+Abramov%2C+Karina+Zainullina%2C+Alexander+Golubev%2C+Sergey+Polezhaev%2C+Daria+Litvintseva%2C+Simon+Karasik%2C+Filipp+Fisin%2C+Sergey+Skvortsov%2C+Maxim+N)
6. Ibragim Badertdinov, Alexander Golubev, Maksim Nekrashevich, Anton Shevtsov, Simon Karasik, Andrei Andriushchenko, Maria Trofimova, Daria Litvintseva, and Boris Yangel. Swe-rebench: An automated pipeline for task collection and decontaminated evaluation of software engineering agents, 2025. URL http… — [arXiv:2505.20411](https://arxiv.org/abs/2505.20411) [find](https://scholar.google.com/scholar?q=Ibragim+Badertdinov%2C+Alexander+Golubev%2C+Maksim+Nekrashevich%2C+Anton+Shevtsov%2C+Simon+Karasik%2C+Andrei+Andriushchenko%2C+Maria+Trofimova%2C+Daria+Litvintseva%2C+and+Boris+Yangel%2E+Swe%2Drebench%3A+An+automated+pipel)
7. Bowen Baker, Ilge Akkaya, Peter Zhokov, Joost Huizinga, Jie Tang, Adrien Ecoffet, Brandon Houghton, Raul Sampedro, and Jeff Clune. Video pretraining (vpt): Learning to act by watching unlabeled online videos. Advances in Neural Information Processing Systems, 35:24639–24654, 2022. [find](https://scholar.google.com/scholar?q=Bowen+Baker%2C+Ilge+Akkaya%2C+Peter+Zhokov%2C+Joost+Huizinga%2C+Jie+Tang%2C+Adrien+Ecoffet%2C+Brandon+Houghton%2C+Raul+Sampedro%2C+and+Jeff+Clune%2E+Video+pretraining+%28vpt%29%3A+Learning+to+act+by+watching+unlabeled+online)
8. Marc G Bellemare, Yavar Naddaf, Joel Veness, and Michael Bowling. The arcade learning environment: An evaluation platform for general agents. Journal of artificial intelligence research, 47:253–279, 2013. [find](https://scholar.google.com/scholar?q=Marc+G+Bellemare%2C+Yavar+Naddaf%2C+Joel+Veness%2C+and+Michael+Bowling%2E+The+arcade+learning+environment%3A+An+evaluation+platform+for+general+agents%2E+Journal+of+artificial+intelligence+research%2C+47%3A253%E2%80%93279%2C+2)
9. Rogerio Bonatti, Dan Zhao, Francesco Bonacci, Dillon Dupont, Sara Abdali, Yinheng Li, Justin Wagle, Kazuhito Koishida, Arthur Bucker, Lawrence Jang, and Zack Hui. Windows agent arena: Evaluating multi-modal os agents at scale. September 2024. [find](https://scholar.google.com/scholar?q=Rogerio+Bonatti%2C+Dan+Zhao%2C+Francesco+Bonacci%2C+Dillon+Dupont%2C+Sara+Abdali%2C+Yinheng+Li%2C+Justin+Wagle%2C+Kazuhito+Koishida%2C+Arthur+Bucker%2C+Lawrence+Jang%2C+and+Zack+Hui%2E+Windows+agent+arena%3A+Evaluating+multi)
10. ByteDance. Seed-thinking-1.6, 2025. URL [https://seed.bytedance.com/zh/seed1_6](https://seed.bytedance.com/zh/seed1_6). [↗](https://seed.bytedance.com/zh/seed1_6)
11. Zehui Chen, Kuikun Liu, Qiuchen Wang, Jiangning Liu, Wenwei Zhang, Kai Chen, and Feng Zhao. [Mindsearch: Mimicking human minds elicits deep ai searcher](https://md.research.elamur.ai/free/en/papers/chen-2024-mindsearch-mimicking-human-minds-elicits/), 2024. URL https://arxiv.org/abs/2407.20183. [↗](https://arxiv.org/abs/2407.20183)
12. Kanzhi Cheng, Qiushi Sun, Yougang Chu, Fangzhi Xu, Yantao Li, Jianbing Zhang, and Zhiyong Wu. [Seeclick: Harnessing gui grounding for advanced visual gui agents](https://md.research.elamur.ai/free/en/papers/cheng-2024-seeclick-harnessing-gui-grounding-advanced/). arXiv preprint arXiv:2401.10935, 2024.
13. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, et al. [Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities](https://md.research.elamur.ai/free/en/papers/comanici-2025-gemini-2-5-pushing-frontier/). arXiv preprint a…
14. Matt Deitke, Christopher Clark, Sangho Lee, Rohun Tripathi, Yue Yang, Jae Sung Park, Mohammadreza Salehi, Niklas Muennighoff, Kyle Lo, Luca Soldaini, et al. Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models. arXiv e-prints, pages arXiv–2409, 2024. [find](https://scholar.google.com/scholar?q=Matt+Deitke%2C+Christopher+Clark%2C+Sangho+Lee%2C+Rohun+Tripathi%2C+Yue+Yang%2C+Jae+Sung+Park%2C+Mohammadreza+Salehi%2C+Niklas+Muennighoff%2C+Kyle+Lo%2C+Luca+Soldaini%2C+et+al%2E+Molmo+and+pixmo%3A+Open+weights+and+open+data)
15. Xiang Deng, Kelvin Guu, Panupong Pasupat, Afra Akyürek, Sheng Zhuang, Wenlong Chen, Tatsunori Hashimoto, Kelvin Guu, and Percy Liang. [Mind2web: Towards a generalist agent for the web](https://md.research.elamur.ai/free/en/papers/deng-2023-mind2web-towards-generalist-agent-web/). In NeurIPS Datasets and Benchmarks, 2023. URL https://arxiv.org/abs/2306.06070. [↗](https://arxiv.org/abs/2306.06070)
16. Linxi Fan, Guanzhi Wang, Yunfan Jiang, Ajay Mandlekar, Yuncong Yang, Haoyi Zhu, Andrew Tang, De-An Huang, Yuke Zhu, and Anima Anandkumar. Minedojo: Building open-ended embodied agents with internet-scale knowledge. Advances in Neural Information Processing Systems, 35:18343–18362, 2022. [find](https://scholar.google.com/scholar?q=Linxi+Fan%2C+Guanzhi+Wang%2C+Yunfan+Jiang%2C+Ajay+Mandlekar%2C+Yuncong+Yang%2C+Haoyi+Zhu%2C+Andrew+Tang%2C+De%2DAn+Huang%2C+Yuke+Zhu%2C+and+Anima+Anandkumar%2E+Minedojo%3A+Building+open%2Dended+embodied+agents+with+internet%2Dsc)
17. Jiazhan Feng, Shijue Huang, Xingwei Qu, Ge Zhang, Yujia Qin, Baoquan Zhong, Chengquan Jiang, Jinxin Chi, and Wanjun Zhong. Retool: Reinforcement learning for strategic tool use in llms, 2025. URL https://arxiv.org/abs/2504.11536. [↗](https://arxiv.org/abs/2504.11536)
18. Zhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen, Yujiu Yang, Minlie Huang, Nan Duan, and Weizhu Chen. [Tora: A tool-integrated reasoning agent for mathematical problem solving](https://md.research.elamur.ai/free/en/papers/gou-2023-tora-tool-integrated-reasoning-agent/), 2024. URL https://arxiv.org/abs/2309.17452. URL https://www.anthropic.com/news/2025. URL https://www.anthropic.com/news/ [↗](https://arxiv.org/abs/2309.17452)
19. Jiawei Gu, Xuhui Jiang, Zhichao Shi, Hexiang Tan, Xuehao Zhai, Chengjin Xu, Wei Li, Yinghan Shen, Shengjie Ma, Honghao Liu, et al. A survey on llm-as-a-judge. arXiv preprint arXiv:2411.15594, 2024. [find](https://scholar.google.com/scholar?q=Jiawei+Gu%2C+Xuhui+Jiang%2C+Zhichao+Shi%2C+Hexiang+Tan%2C+Xuehao+Zhai%2C+Chengjin+Xu%2C+Wei+Li%2C+Yinghan+Shen%2C+Shengjie+Ma%2C+Honghao+Liu%2C+et+al%2E+A+survey+on+llm%2Das%2Da%2Djudge%2E+arXiv+preprint+arXiv%3A2411%2E15594%2C+2024%2E)
20. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. [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, 2025.
21. Hongcheng Guo, Jian Yang, Jiaheng Liu, Liqun Yang, Linzheng Chai, Jiaqi Bai, Junran Peng, Xiaorong Hu, Chao Chen, Dongfeng Zhang, Xu Shi, Tieqiao Zheng, Liangfan Zheng, Bo Zhang, Ke Xu, and Zhoujun Li. Owl: A large language model for it operations, 2024. URL https://arxiv.org/abs/2309.09298. — [arXiv:2309.09298](https://arxiv.org/abs/2309.09298) [↗](https://arxiv.org/abs/2309.09298)
22. Wenyi Hong, Weihan Wang, Qingsong Lv, Jiazheng Xu, Wenmeng Yu, Junhui Ji, Yan Wang, Zihan Wang, Yuxiao Dong, Ming Ding, et al. [Cogagent: A visual language model for gui agents](https://md.research.elamur.ai/free/en/papers/hong-2023-cogagent-visual-language-model/). In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14281–14290, 2024.
23. Lanxiang Hu, Mingjia Huo, Yuxuan Zhang, Haoyang Yu, Eric P. Xing, Ion Stoica, Tajana Rosing, Haojian Jin, and Hao Zhang. lmgame-bench: How good are llms at playing games?, 2025. URL https://arxiv.org/abs/2505.15146. [↗](https://arxiv.org/abs/2505.15146)
24. Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, et al. Os agents: A survey on mllm-based agents for general computing devices use. arXiv preprint arXiv:2508.04482, 2025. — [arXiv:2508.04482](https://arxiv.org/abs/2508.04482) [find](https://scholar.google.com/scholar?q=Xueyu+Hu%2C+Tao+Xiong%2C+Biao+Yi%2C+Zishu+Wei%2C+Ruixuan+Xiao%2C+Yurun+Chen%2C+Jiasheng+Ye%2C+Meiling+Tao%2C+Xiangxin+Zhou%2C+Ziyu+Zhao%2C+et+al%2E+Os+agents%3A+A+survey+on+mllm%2Dbased+agents+for+general+computing+devices+use)
25. Lisheng Huang, Yichen Liu, Jinhao Jiang, Rongxiang Zhang, Jiahao Yan, Junyi Li, and Wayne Xin Zhao. Manusearch: Democratizing deep search in large language models with a transparent and open multi-agent framework, 2025. URL https://arxiv.org/abs/2505.18105. [↗](https://arxiv.org/abs/2505.18105)
26. Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, et al. [Openai o1 system card](https://md.research.elamur.ai/free/en/papers/openai-2024-openai-o1-system-card/). arXiv preprint arXiv:2412.16720, 2024.
27. Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan. [SWE-bench: Can language models resolve real-world github issues?](https://md.research.elamur.ai/free/en/papers/jimenez-2024-swe-bench-can-language-models/) arXiv preprint arXiv:2310.06770, 2023.
28. Ehud Karpas, Omri Abend, Yonatan Belinkov, Barak Lenz, Opher Lieber, Nir Ratner, Yoav Shoham, Hofit Bata, Yoav Levine, Kevin Leyton-Brown, et al. MRKL systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning. arXiv preprin… — [arXiv:2205.00445](https://arxiv.org/abs/2205.00445) [find](https://scholar.google.com/scholar?q=Ehud+Karpas%2C+Omri+Abend%2C+Yonatan+Belinkov%2C+Barak+Lenz%2C+Opher+Lieber%2C+Nir+Ratner%2C+Yoav+Shoham%2C+Hofit+Bata%2C+Yoav+Levine%2C+Kevin+Leyton%2DBrown%2C+et+al%2E+MRKL+systems%3A+A+modular%2C+neuro%2Dsymbolic+architecture+t)
29. 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. Websailor: Navigating super-human reasoning for web agent, 2… [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)
30. Muyao Li, Zihao Wang, Kaichen He, Xiaojian Ma, and Yitao Liang. Jarvis-vla: Post-training large-scale vision language models to play visual games with keyboards and mouse. arXiv preprint arXiv:2503.16365, 2025. [find](https://scholar.google.com/scholar?q=Muyao+Li%2C+Zihao+Wang%2C+Kaichen+He%2C+Xiaojian+Ma%2C+and+Yitao+Liang%2E+Jarvis%2Dvla%3A+Post%2Dtraining+large%2Dscale+vision+language+models+to+play+visual+games+with+keyboards+and+mouse%2E+arXiv+preprint+arXiv%3A2503%2E16)
31. Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, and Zhicheng Dou. [Search-o1: Agentic search-enhanced large reasoning models](https://md.research.elamur.ai/free/en/papers/li-2025-search-o1-agentic-search-enhanced/), 2025. URL https://arxiv.org/abs/2501.05366. [↗](https://arxiv.org/abs/2501.05366)
32. Xuefeng Li, Haoyang Zou, and Pengfei Liu. Torl: Scaling tool-integrated rl, 2025. URL https://arxiv.org/abs/2503.23383. [↗](https://arxiv.org/abs/2503.23383)
33. Bang Liu, Xinfeng Li, Jiayi Zhang, Jinlin Wang, Tanjin He, Sirui Hong, Hongzhang Liu, Shaokun Zhang, Kaitao Song, Kunlun Zhu, et al. Advances and challenges in foundation agents: From brain-inspired intelligence to evolutionary, collaborative, and safe systems. arXiv preprint arXiv:2504.01990, 2025. — [arXiv:2504.01990](https://arxiv.org/abs/2504.01990) [find](https://scholar.google.com/scholar?q=Bang+Liu%2C+Xinfeng+Li%2C+Jiayi+Zhang%2C+Jinlin+Wang%2C+Tanjin+He%2C+Sirui+Hong%2C+Hongzhang+Liu%2C+Shaokun+Zhang%2C+Kaitao+Song%2C+Kunlun+Zhu%2C+et+al%2E+Advances+and+challenges+in+foundation+agents%3A+From+brain%2Dinspired+i)
34. Fanbin Lu, Zhisheng Zhong, Shu Liu, Chi-Wing Fu, and Jiaya Jia. Arpo: End-to-end policy optimization for gui agents with experience replay. arXiv preprint arXiv:2505.16282, 2025. — [arXiv:2505.16282](https://arxiv.org/abs/2505.16282) [find](https://scholar.google.com/scholar?q=Fanbin+Lu%2C+Zhisheng+Zhong%2C+Shu+Liu%2C+Chi%2DWing+Fu%2C+and+Jiaya+Jia%2E+Arpo%3A+End%2Dto%2Dend+policy+optimization+for+gui+agents+with+experience+replay%2E+arXiv+preprint+arXiv%3A2505%2E16282%2C+2025%2E+%E2%80%94+%5BarXiv%3A2505%2E16282%5D%28)
35. Qinyu Luo, Yining Ye, Shihao Liang, Zhong Zhang, Yujia Qin, Yaxi Lu, Yesai Wu, Xin Cong, Yankai Lin, Yingli Zhang, Xiaoyin Che, Zhiyuan Liu, and Maosong Sun. Repoagent: An llm-powered open-source framework for repository-level code documentation generation. arXiv preprint arXiv:2402.16667, 2024. URL… [find](https://scholar.google.com/scholar?q=Qinyu+Luo%2C+Yining+Ye%2C+Shihao+Liang%2C+Zhong+Zhang%2C+Yujia+Qin%2C+Yaxi+Lu%2C+Yesai+Wu%2C+Xin+Cong%2C+Yankai+Lin%2C+Yingli+Zhang%2C+Xiaoyin+Che%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+Repoagent%3A+An+llm%2Dpowered+open%2Dsource+fram)
36. Weiyu Ma, Qirui Mi, Yongcheng Zeng, Xue Yan, Runji Lin, Yuqiao Wu, Jun Wang, and Haifeng Zhang. Large language models play starcraft ii: Benchmarks and a chain of summarization approach. Advances in Neural Information Processing Systems, 37:133386–133442, 2024. [find](https://scholar.google.com/scholar?q=Weiyu+Ma%2C+Qirui+Mi%2C+Yongcheng+Zeng%2C+Xue+Yan%2C+Runji+Lin%2C+Yuqiao+Wu%2C+Jun+Wang%2C+and+Haifeng+Zhang%2E+Large+language+models+play+starcraft+ii%3A+Benchmarks+and+a+chain+of+summarization+approach%2E+Advances+in+N)
37. Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, et al. Human-level control through deep reinforcement learning. nature, 518(7540):529–533, 2015. [find](https://scholar.google.com/scholar?q=Volodymyr+Mnih%2C+Koray+Kavukcuoglu%2C+David+Silver%2C+Andrei+A+Rusu%2C+Joel+Veness%2C+Marc+G+Bellemare%2C+Alex+Graves%2C+Martin+Riedmiller%2C+Andreas+K+Fidjeland%2C+Georg+Ostrovski%2C+et+al%2E+Human%2Dlevel+control+through+)
38. MoonshotAI. Kimi-researcher: End-to-end rl training for emerging agentic capabilities. [https://moonshotai.github.io/Kimi-Researcher/](https://moonshotai.github.io/Kimi-Researcher/), 2025. [↗](https://moonshotai.github.io/Kimi-Researcher/)
39. Dang Nguyen, Jian Chen, Yu Wang, Gang Wu, Namyong Park, Zhengmian Hu, Hanjia Lyu, Junda Wu, Ryan Aponte, Yu Xia, et al. Gui agents: A survey. arXiv preprint arXiv:2412.13501, 2024. [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+et+al%2E+Gui+agents%3A+A+survey%2E+arXiv+preprint+arXiv%3A2412%2E13501%2C+2024%2E)
40. OpenAI. OpenAI: Introducing ChatGPT, 2022. URL [https://openai.com/blog/chatgpt](https://openai.com/blog/chatgpt). [↗](https://openai.com/blog/chatgpt)
41. OpenAI. Introducing gpt 5, 2025. URL [https://openai.com/index/introducing-gpt-5/](https://openai.com/index/introducing-gpt-5/). [↗](https://openai.com/index/introducing-gpt-5/)
42. OpenAI. Introducing deep research - openai. [https://openai.com/index/introducing-deep-research/](https://openai.com/index/introducing-deep-research/), 2025. Openai o3 and o4-mini system card. https://cdn.openai.com/pdf/ [↗](https://openai.com/index/introducing-deep-research/)
43. OpenAI. 2221c875-02dc-4789-800b-e7758f3722c1/o3-and-o4-mini-system-card.pdf/, 2025. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2221c875%2D02dc%2D4789%2D800b%2De7758f3722c1%2Fo3%2Dand%2Do4%2Dmini%2Dsystem%2Dcard%2Epdf%2F%2C+2025%2E)
44. OpenAI. Computer-using agent (cua). [https://openai.com/index/computer-using-agent/](https://openai.com/index/computer-using-agent/), 2025. Research preview / blog. [↗](https://openai.com/index/computer-using-agent/)
45. openai. Operator, 2025. URL [https://openai.com/index/introducing-operator/](https://openai.com/index/introducing-operator/). [↗](https://openai.com/index/introducing-operator/)
46. Jiayi Pan, Xingyao Wang, Graham Neubig, Navdeep Jaitly, Heng Ji, Alane Suhr, and Yizhe Zhang. Training software engineering agents and verifiers with swe-gym, 2025. URL https://arxiv.org/abs/2412.21139. [↗](https://arxiv.org/abs/2412.21139)
47. Yujia Qin, Cheng Qian, Jing Yi, Weize Chen, Yankai Lin, Xu Han, Zhiyuan Liu, Maosong Sun, and Jie Zhou. Exploring mode connectivity for pre-trained language models. In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang, editors, Proceedings of the 2022 Conference on Empirical Methods in Natural Languag… [find](https://scholar.google.com/scholar?q=Yujia+Qin%2C+Cheng+Qian%2C+Jing+Yi%2C+Weize+Chen%2C+Yankai+Lin%2C+Xu+Han%2C+Zhiyuan+Liu%2C+Maosong+Sun%2C+and+Jie+Zhou%2E+Exploring+mode+connectivity+for+pre%2Dtrained+language+models%2E+In+Yoav+Goldberg%2C+Zornitsa+Kozareva)
48. Yujia Qin, Yining Ye, Junjie Fang, Haoming Wang, Shihao Liang, Shizuo Tian, Junda Zhang, Jiahao Li, Yunxin Li, Shijue Huang, et al. [Ui-tars: Pioneering automated gui interaction with native agents](https://md.research.elamur.ai/free/en/papers/qin-2025-ui-tars-pioneering-automated/). arXiv preprint arXiv:2501.12326, 2025.
49. Jiahao Qiu, Xuan Qi, Tongcheng Zhang, Xinzhe Juan, Jiacheng Guo, Yifu Lu, Yimin Wang, Zixin Yao, Qihan Ren, Xun Jiang, Xing Zhou, Dongrui Liu, Ling Yang, Yue Wu, Kaixuan Huang, Shilong Liu, Hongru Wang, and Mengdi Wang. Alita: Generalist agent enabling scalable agentic reasoning with minimal predefi… — [arXiv:2505.20286](https://arxiv.org/abs/2505.20286) [find](https://scholar.google.com/scholar?q=Jiahao+Qiu%2C+Xuan+Qi%2C+Tongcheng+Zhang%2C+Xinzhe+Juan%2C+Jiacheng+Guo%2C+Yifu+Lu%2C+Yimin+Wang%2C+Zixin+Yao%2C+Qihan+Ren%2C+Xun+Jiang%2C+Xing+Zhou%2C+Dongrui+Liu%2C+Ling+Yang%2C+Yue+Wu%2C+Kaixuan+Huang%2C+Shilong+Liu%2C+Hongru+Wan)
50. Maria Abi Raad, Arun Ahuja, Catarina Barros, Frederic Besse, Andrew Bolt, Adrian Bolton, Bethanie Brownfield, Gavin Buttimore, Max Cant, Sarah Chakera, et al. Scaling instructable agents across many simulated worlds. arXiv preprint arXiv:2404.10179, 2024. — [arXiv:2404.10179](https://arxiv.org/abs/2404.10179) [find](https://scholar.google.com/scholar?q=Maria+Abi+Raad%2C+Arun+Ahuja%2C+Catarina+Barros%2C+Frederic+Besse%2C+Andrew+Bolt%2C+Adrian+Bolton%2C+Bethanie+Brownfield%2C+Gavin+Buttimore%2C+Max+Cant%2C+Sarah+Chakera%2C+et+al%2E+Scaling+instructable+agents+across+many+s)
51. Christopher Rawles, Sarah Clinckemaillie, Yifan Chang, Jonathan Waltz, Gabrielle Lau, Marybeth Fair, Alice Li, William Bishop, Wei Li, Folawiyo Campbell-Ajala, Daniel Toyama, Robert Berry, Divya Tyamagundlu, Timothy Lillicrap, and Oriana Riva. Androidworld: A dynamic benchmarking environment for aut… [find](https://scholar.google.com/scholar?q=Christopher+Rawles%2C+Sarah+Clinckemaillie%2C+Yifan+Chang%2C+Jonathan+Waltz%2C+Gabrielle+Lau%2C+Marybeth+Fair%2C+Alice+Li%2C+William+Bishop%2C+Wei+Li%2C+Folawiyo+Campbell%2DAjala%2C+Daniel+Toyama%2C+Robert+Berry%2C+Divya+Tyama)
52. Scott Reed, Konrad Zolna, Emilio Parisotto, Sergio Gomez Colmenarejo, Alexander Novikov, Gabriel Barth-Maron, Mai Gimenez, Yury Sulsky, Jackie Kay, Jost Tobias Springenberg, et al. A generalist agent. arXiv preprint arXiv:2205.06175, 2022. [find](https://scholar.google.com/scholar?q=Scott+Reed%2C+Konrad+Zolna%2C+Emilio+Parisotto%2C+Sergio+Gomez+Colmenarejo%2C+Alexander+Novikov%2C+Gabriel+Barth%2DMaron%2C+Mai+Gimenez%2C+Yury+Sulsky%2C+Jackie+Kay%2C+Jost+Tobias+Springenberg%2C+et+al%2E+A+generalist+agent%2E)
53. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. [Toolformer: Language models can teach themselves to use tools](https://md.research.elamur.ai/free/en/papers/schick-2023-toolformer-language-models-can-teach/). arXiv preprint arXiv:2302.04761, 2023.
54. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347, 2017. [find](https://scholar.google.com/scholar?q=John+Schulman%2C+Filip+Wolski%2C+Prafulla+Dhariwal%2C+Alec+Radford%2C+and+Oleg+Klimov%2E+Proximal+policy+optimization+algorithms%2E+arXiv+preprint+arXiv%3A1707%2E06347%2C+2017%2E)
55. ByteDance Seed. Ui-tars-1.5. [https://seed-tars.com/1.5](https://seed-tars.com/1.5), 2025. [↗](https://seed-tars.com/1.5)
56. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. [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/), 2024. URL https://arxiv.org/abs/2402.03300. [↗](https://arxiv.org/abs/2402.03300)
57. Yucheng Shi, Wenhao Yu, Zaitang Li, Yonglin Wang, Hongming Zhang, Ninghao Liu, Haitao Mi, and Dong Yu. Mobilegui-rl: Advancing mobile gui agent through reinforcement learning in online environment. arXiv preprint arXiv:2507.05720, 2025. — [arXiv:2507.05720](https://arxiv.org/abs/2507.05720) [find](https://scholar.google.com/scholar?q=Yucheng+Shi%2C+Wenhao+Yu%2C+Zaitang+Li%2C+Yonglin+Wang%2C+Hongming+Zhang%2C+Ninghao+Liu%2C+Haitao+Mi%2C+and+Dong+Yu%2E+Mobilegui%2Drl%3A+Advancing+mobile+gui+agent+through+reinforcement+learning+in+online+environment%2E+ar)
58. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. [Reflexion: Language agents with verbal reinforcement learning](https://md.research.elamur.ai/free/en/papers/shinn-2023-reflexion-language-agents-verbal-reinforcement/). Advances in Neural Information Processing Systems, 36:8634–8652, 2023.
59. David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, et al. Mastering the game of go without human knowledge. nature, 550(7676):354–359, 2017. [find](https://scholar.google.com/scholar?q=David+Silver%2C+Julian+Schrittwieser%2C+Karen+Simonyan%2C+Ioannis+Antonoglou%2C+Aja+Huang%2C+Arthur+Guez%2C+Thomas+Hubert%2C+Lucas+Baker%2C+Matthew+Lai%2C+Adrian+Bolton%2C+et+al%2E+Mastering+the+game+of+go+without+human+kn)
60. Huatong Song, Jinhao Jiang, Wenqing Tian, Zhipeng Chen, Yuhuan Wu, Jiahao Zhao, Yingqian Min, Wayne Xin Zhao, Lei Fang, and Ji-Rong Wen. R1-searcher++: Incentivizing the dynamic knowledge acquisition of llms via reinforcement learning. arXiv preprint arXiv:2505.17005, 2025. — [arXiv:2505.17005](https://arxiv.org/abs/2505.17005) [find](https://scholar.google.com/scholar?q=Huatong+Song%2C+Jinhao+Jiang%2C+Wenqing+Tian%2C+Zhipeng+Chen%2C+Yuhuan+Wu%2C+Jiahao+Zhao%2C+Yingqian+Min%2C+Wayne+Xin+Zhao%2C+Lei+Fang%2C+and+Ji%2DRong+Wen%2E+R1%2Dsearcher%2B%2B%3A+Incentivizing+the+dynamic+knowledge+acquisition+)
61. Shuang Sun, Huatong Song, Yuhao Wang, Ruiyang Ren, Jinhao Jiang, Junjie Zhang, Fei Bai, Jia Deng, Wayne Xin Zhao, Zheng Liu, Lei Fang, Zhongyuan Wang, and Ji-Rong Wen. Simpledeepsearcher: Deep information seeking via web-powered reasoning trajectory synthesis. CoRR, abs/2505.16834, 2025. doi: 10.485… [find](https://scholar.google.com/scholar?q=Shuang+Sun%2C+Huatong+Song%2C+Yuhao+Wang%2C+Ruiyang+Ren%2C+Jinhao+Jiang%2C+Junjie+Zhang%2C+Fei+Bai%2C+Jia+Deng%2C+Wayne+Xin+Zhao%2C+Zheng+Liu%2C+Lei+Fang%2C+Zhongyuan+Wang%2C+and+Ji%2DRong+Wen%2E+Simpledeepsearcher%3A+Deep+informa)
62. Fei Tang, Haolei Xu, Hang Zhang, Siqi Chen, Xingyu Wu, Yongliang Shen, Wenqi Zhang, Guiyang Hou, Zeqi Tan, Yuchen Yan, et al. A survey on (m) llm-based gui agents. arXiv preprint arXiv:2504.13865, 2025. — [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+et+al%2E+A+survey+on+%28m%29+llm%2Dbased+gui+agents%2E+arXiv+preprint+arXiv%3A2504%2E13865%2C+202)
63. Kimi Team. [Kimi k2: Open agentic intelligence](https://md.research.elamur.ai/free/en/papers/kimi-team-2025-kimi-k2-open-agentic/), 2025. URL https://arxiv.org/abs/2507.20534. [↗](https://arxiv.org/abs/2507.20534)
64. Qwen Team. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/), 2025. URL https://arxiv.org/abs/2505.09388. [↗](https://arxiv.org/abs/2505.09388)
65. The Terminal-Bench Team. Terminal-bench: A benchmark for ai agents in terminal environments, Apr 2025. URL [https://github.com/laude-institute/terminal-bench](https://github.com/laude-institute/terminal-bench). [↗](https://github.com/laude-institute/terminal-bench)
66. Oriol Vinyals, Igor Babuschkin, Wojciech M Czarnecki, Michaël Mathieu, Andrew Dudzik, Junyoung Chung, David H Choi, Richard Powell, Timo Ewalds, Petko Georgiev, et al. Grandmaster level in starcraft ii using multi-agent reinforcement learning. nature, 575(7782):350–354, 2019. [find](https://scholar.google.com/scholar?q=Oriol+Vinyals%2C+Igor+Babuschkin%2C+Wojciech+M+Czarnecki%2C+Micha%C3%ABl+Mathieu%2C+Andrew+Dudzik%2C+Junyoung+Chung%2C+David+H+Choi%2C+Richard+Powell%2C+Timo+Ewalds%2C+Petko+Georgiev%2C+et+al%2E+Grandmaster+level+in+starcraft+i)
67. Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291, 2023. [find](https://scholar.google.com/scholar?q=Guanzhi+Wang%2C+Yuqi+Xie%2C+Yunfan+Jiang%2C+Ajay+Mandlekar%2C+Chaowei+Xiao%2C+Yuke+Zhu%2C+Linxi+Fan%2C+and+Anima+Anandkumar%2E+Voyager%3A+An+open%2Dended+embodied+agent+with+large+language+models%2E+arXiv+preprint+arXiv%3A23)
68. Hongru Wang, Cheng Qian, Wanjun Zhong, Xiusi Chen, Jiahao Qiu, Shijue Huang, Bowen Jin, Mengdi Wang, Kam-Fai Wong, and Heng Ji. Acting less is reasoning more! teaching model to act efficiently, 2025. URL https://arxiv.org/abs/2504.14870. — [arXiv:2504.14870](https://arxiv.org/abs/2504.14870) [↗](https://arxiv.org/abs/2504.14870)
69. Shuai Wang, Weiwen Liu, Jingxuan Chen, Yuqi Zhou, Weinan Gan, Xingshan Zeng, Yuhan Che, Shuai Yu, Xinlong Hao, Kun Shao, et al. Gui agents with foundation models: A comprehensive survey. arXiv preprint arXiv:2411.04890, 2024. — [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+et+al%2E+Gui+agents+with+foundation+models%3A+A+comprehensive+survey%2E+arXiv+preprin)
70. Xingyao Wang, Boxuan Li, Yufan Song, Frank F. Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, Hoang H. Tran, Fuqiang Li, Ren Ma, Mingzhang Zheng, Bill Qian, Yanjun Shao, Niklas Muennighoff, Yizhe Zhang, Binyuan Hui, Junyang Lin, Robert Brennan, Hao Peng, Heng Ji, a… — [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://md.research.elamur.ai/free/en/papers/wang-2024-openhands-open-platform-ai/)
71. Zihao Wang, Shaofei Cai, Anji Liu, Yonggang Jin, Jinbing Hou, Bowei Zhang, Haowei Lin, Zhaofeng He, Zilong Zheng, Yaodong Yang, et al. Jarvis-1: Open-world multi-task agents with memory-augmented multimodal language models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024. [find](https://scholar.google.com/scholar?q=Zihao+Wang%2C+Shaofei+Cai%2C+Anji+Liu%2C+Yonggang+Jin%2C+Jinbing+Hou%2C+Bowei+Zhang%2C+Haowei+Lin%2C+Zhaofeng+He%2C+Zilong+Zheng%2C+Yaodong+Yang%2C+et+al%2E+Jarvis%2D1%3A+Open%2Dworld+multi%2Dtask+agents+with+memory%2Daugmented+mult)
72. Jason Wei, Zhiqing Sun, Spencer Papay, Scott McKinney, Jeffrey Han, Isa Fulford, Hyung Won Chung, Alex Tachard Passos, William Fedus, and Amelia Glaese. Browsecomp: A simple yet challenging benchmark for browsing agents. arXiv preprint arXiv:2504.12516, 2025. [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+Browsecomp%3A+A+simple+yet+challenging+benchmark+)
73. Zhiyong Wu, Zhenyu Wu, Fangzhi Xu, Yian Wang, Qiushi Sun, Chengyou Jia, Kanzhi Cheng, Zichen Ding, Liheng Chen, Paul Pu Liang, et al. [Os-atlas: A foundation action model for generalist gui agents](https://md.research.elamur.ai/free/en/papers/wu-2024-os-atlas-foundation-action-model/). arXiv preprint arXiv:2410.23218, 2024.
74. Tianbao Xie, Danyang Zhang, Jixuan Chen, Xiaochuan Li, Siheng Zhao, Ruisheng Cao, Toh J Hua, Zhoujun Cheng, Dongchan Shin, Fangyu Lei, et al. [Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments](https://md.research.elamur.ai/free/en/papers/xie-2024-osworld-benchmarking-multimodal-agents-open/). Advances in Neural Information Processing Systems, 37:52040–52094,…
75. Yiheng Xu, Zekun Wang, Junli Wang, Dunjie Lu, Tianbao Xie, Amrita Saha, Doyen Sahoo, Tao Yu, and Caiming Xiong. Aguvis: Unified pure vision agents for autonomous gui interaction. arXiv preprint arXiv:2412.04454, 2024. — [arXiv:2412.04454](https://arxiv.org/abs/2412.04454) [find](https://scholar.google.com/scholar?q=Yiheng+Xu%2C+Zekun+Wang%2C+Junli+Wang%2C+Dunjie+Lu%2C+Tianbao+Xie%2C+Amrita+Saha%2C+Doyen+Sahoo%2C+Tao+Yu%2C+and+Caiming+Xiong%2E+Aguvis%3A+Unified+pure+vision+agents+for+autonomous+gui+interaction%2E+arXiv+preprint+arXiv%3A)
76. Tianci Xue, Weijian Qi, Tianneng Shi, Chan Hee Song, Boyu Gou, Dawn Song, Huan Sun, and Yu Su. An illusion of progress? assessing the current state of web agents. 2025. URL https://arxiv.org/abs/2504.01382. [↗](https://arxiv.org/abs/2504.01382)
77. John Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press. [Swe-agent: Agent-computer interfaces enable automated software engineering](https://md.research.elamur.ai/free/en/papers/yang-2024-swe-agent-agent-computer-interfaces/), 2024. URL https://arxiv.org/abs/2405.15793. [↗](https://arxiv.org/abs/2405.15793)
78. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. [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), 2023.
79. Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Yu Yue, Tiantian Fan, Gaohong Liu, Lingjun Liu, Xin Liu, Haibin Lin, Zhiqi Lin, Bole Ma, Guangming Sheng, Yuxuan Tong, Chi Zhang, Mofan Zhang, Wang Zhang, Hang Zhu, Jinhua Zhu, Jiaze Chen, Jiangjie Chen, Chengyi Wang, Hongli Yu, Weinan D… — [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://md.research.elamur.ai/free/en/papers/yu-2025-dapo-open-source-llm-reinforcement/)
80. Haoqi Yuan, Chi Zhang, Hongcheng Wang, Feiyang Xie, Penglin Cai, Hao Dong, and Zongqing Lu. Plan4mc: Skill reinforcement learning and planning for open-world minecraft tasks. arXiv preprint arXiv:2303.16563, 2(5), 2023. — [arXiv:2303.16563](https://arxiv.org/abs/2303.16563) [find](https://scholar.google.com/scholar?q=Haoqi+Yuan%2C+Chi+Zhang%2C+Hongcheng+Wang%2C+Feiyang+Xie%2C+Penglin+Cai%2C+Hao+Dong%2C+and+Zongqing+Lu%2E+Plan4mc%3A+Skill+reinforcement+learning+and+planning+for+open%2Dworld+minecraft+tasks%2E+arXiv+preprint+arXiv%3A2303)
81. Yufeng Yuan, Yu Yue, Ruofei Zhu, Tiantian Fan, and Lin Yan. What’s behind ppo’s collapse in long-cot? value optimization holds the secret, 2025. URL https://arxiv.org/abs/2503.01491. — [arXiv:2503.01491](https://arxiv.org/abs/2503.01491) [↗](https://arxiv.org/abs/2503.01491)
82. Yu Yue, Yufeng Yuan, Qiying Yu, Xiaochen Zuo, Ruofei Zhu, Wenyuan Xu, Jiaze Chen, Chengyi Wang, TianTian Fan, Zhengyin Du, Xiangpeng Wei, Xiangyu Yu, Gaohong Liu, Juncai Liu, Lingjun Liu, Haibin Lin, Zhiqi Lin, Bole Ma, Chi Zhang, Mofan Zhang, Wang Zhang, Hang Zhu, Ru Zhang, Xin Liu, Mingxuan Wang,… [find](https://scholar.google.com/scholar?q=Yu+Yue%2C+Yufeng+Yuan%2C+Qiying+Yu%2C+Xiaochen+Zuo%2C+Ruofei+Zhu%2C+Wenyuan+Xu%2C+Jiaze+Chen%2C+Chengyi+Wang%2C+TianTian+Fan%2C+Zhengyin+Du%2C+Xiangpeng+Wei%2C+Xiangyu+Yu%2C+Gaohong+Liu%2C+Juncai+Liu%2C+Lingjun+Liu%2C+Haibin+Lin%2C+)
83. Daoguang Zan, Zhirong Huang, Wei Liu, Hanwu Chen, Linhao Zhang, Shulin Xin, Lu Chen, Qi Liu, Xiaojian Zhong, Aoyan Li, Siyao Liu, Yongsheng Xiao, Liangqiang Chen, Yuyu Zhang, Jing Su, Tianyu Liu, Rui Long, Kai Shen, and Liang Xiang. Multi-swe-bench: A multilingual benchmark for issue resolving, 2025… — [arXiv:2504.02605](https://arxiv.org/abs/2504.02605) [find](https://scholar.google.com/scholar?q=Daoguang+Zan%2C+Zhirong+Huang%2C+Wei+Liu%2C+Hanwu+Chen%2C+Linhao+Zhang%2C+Shulin+Xin%2C+Lu+Chen%2C+Qi+Liu%2C+Xiaojian+Zhong%2C+Aoyan+Li%2C+Siyao+Liu%2C+Yongsheng+Xiao%2C+Liangqiang+Chen%2C+Yuyu+Zhang%2C+Jing+Su%2C+Tianyu+Liu%2C+Rui+)
84. Aohan Zeng, Xin Lv, Qinkai Zheng, Zhenyu Hou, Bin Chen, Chengxing Xie, Cunxiang Wang, Da Yin, Hao Zeng, Jiajie Zhang, et al. [Glm-4.5: Agentic, reasoning, and coding (arc) foundation models](https://md.research.elamur.ai/free/en/papers/team-2025-4-glm-4-5-agentic/). arXiv preprint arXiv:2508.06471, 2025.
85. Ceyao Zhang, Kaijie Yang, Siyi Hu, Zihao Wang, Guanghe Li, Yihang Sun, Cheng Zhang, Zhaowei Zhang, Anji Liu, Song-Chun Zhu, et al. Proagent: building proactive cooperative agents with large language models. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 17591–1759… [find](https://scholar.google.com/scholar?q=Ceyao+Zhang%2C+Kaijie+Yang%2C+Siyi+Hu%2C+Zihao+Wang%2C+Guanghe+Li%2C+Yihang+Sun%2C+Cheng+Zhang%2C+Zhaowei+Zhang%2C+Anji+Liu%2C+Song%2DChun+Zhu%2C+et+al%2E+Proagent%3A+building+proactive+cooperative+agents+with+large+language+m)
86. Chaoyun Zhang, Shilin He, Jiaxu Qian, Bowen Li, Liqun Li, Si Qin, Yu Kang, Minghua Ma, Guyue Liu, Qingwei Lin, et al. Large language model-brained gui agents: A survey. arXiv preprint arXiv:2411.18279, 2024. — [arXiv:2411.18279](https://arxiv.org/abs/2411.18279) [find](https://scholar.google.com/scholar?q=Chaoyun+Zhang%2C+Shilin+He%2C+Jiaxu+Qian%2C+Bowen+Li%2C+Liqun+Li%2C+Si+Qin%2C+Yu+Kang%2C+Minghua+Ma%2C+Guyue+Liu%2C+Qingwei+Lin%2C+et+al%2E+Large+language+model%2Dbrained+gui+agents%3A+A+survey%2E+arXiv+preprint+arXiv%3A2411%2E18279)
87. Peilin Zhou, Bruce Leon, Xiang Ying, Can Zhang, Yifan Shao, Qichen Ye, Dading Chong, Zhiling Jin, Chenxuan Xie, Meng Cao, et al. Browsecomp-zh: Benchmarking web browsing ability of large language models in chinese. arXiv preprint arXiv:2504.19314, 2025. — [arXiv:2504.19314](https://arxiv.org/abs/2504.19314) [find](https://scholar.google.com/scholar?q=Peilin+Zhou%2C+Bruce+Leon%2C+Xiang+Ying%2C+Can+Zhang%2C+Yifan+Shao%2C+Qichen+Ye%2C+Dading+Chong%2C+Zhiling+Jin%2C+Chenxuan+Xie%2C+Meng+Cao%2C+et+al%2E+Browsecomp%2Dzh%3A+Benchmarking+web+browsing+ability+of+large+language+mode)
88. Shuyan Zhou, Daniel Wu, Tatsunori Hashimoto, Nathanael Schärli, et al. [Webarena: A realistic web environment for building autonomous agents](https://md.research.elamur.ai/free/en/papers/zhou-2023-webarena-realistic-web-environment-building/). arXiv preprint arXiv:2307.13854, 2023. Contributions The authors are listed alphabetically by first name, with some names corresponding to internal aliases use…

*Updated 1 November 2026*