Elamur Research⌕
☰
home / papers / 2024 / Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization

Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization

Paper · 2024 · Wenqi Zhang, Ke Tang, Hai Wu et al.

Summary

Most LLM-based agents depend on hand-written prompts that fix task rules and behavior. They cannot improve through experience, so they struggle in dynamic multi-agent settings with hidden information. Agent-Pro tackles this by treating policy learning as gradient-free prompt optimization, with no parameter updates.

The framework has three parts:

  • Belief-aware decision making. Before each action, the agent forms a self-belief and a world-belief.
  • Policy-level reflection. After playing, the agent reviews whole trajectories, its beliefs and the delayed outcomes, and corrects irrational beliefs. It does not fix single actions, as Reflexion does. The corrections are distilled into Behavioral Guidelines and World Modeling instructions.
  • Policy search. A depth-first search over candidate policies keeps only updates that raise payoffs.

The authors test the framework on Blackjack and multi-player Limit Texas Hold'em. Agent-Pro beats vanilla LLMs and specialized game models. Over time it develops human-like tactics such as bluffing and cutting losses. This matters because it shows LLM agents can refine their strategy through interaction alone, which is relevant to negotiation-like real-world tasks.

Key points

  • Backbones and learning curves. Agent-Pro was built on GPT-4, GPT-3.5 and Llama-2-70B. The GPT-based versions gained up to about +2.1 and +2.3 chips early in learning. Llama-2-70B first got worse, then recovered by +0.6 chips.
  • Strategy evolution. On 20 hand-picked hard Texas Hold'em games, Fold and Raise frequencies across PreFlop, Flop, Turn and River were tracked. Behavior shifted from rigid early folding, to cautious, to flexible and proactive play.
  • Results by hand strength. Agent-Pro wins more with strong hands and loses less with weak ones. With medium-strength hands it improves by more than 80%.
  • Comparison with DMC. The GPT-4 version clearly beats DMC and nears human level. The GPT-3.5 and Llama versions still trail DMC.
  • Limitations and code. Results depend heavily on the base model's reasoning ability, and a gap remains to state-of-the-art solvers such as CFR plus. Code is available at github.com/zwq2018/Agent-Pro.

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

🎓Zhejiang UniversityHangzhou · China172 works · 12,988 citations🏛️Chinese Academy of SciencesBeijing · China194 works · 23,906 citations🔬Institute of SoftwareBeijing · China21 works · 4,980 citations🎓Beijing University of TechnologyBeijing · China13 works · 1,910 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

Cite

Cite as Wenqi Zhang, Ke Tang, Hai Wu, Mengna Wang, Yongliang Shen, Guiyang Hou, Zeqi Tan, Peng Li, Yueting Zhuang and Weiming Lu. 2024. Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization. Proceedings of the 62nd 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. DOI 10.18653/v1/2024.acl-long.292

@inproceedings{zhang2024agent,
  title = {{Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization}},
  author = {Wenqi Zhang, Ke Tang, Hai Wu, Mengna Wang, Yongliang Shen, Guiyang Hou, Zeqi Tan, Peng Li, Yueting Zhuang and Weiming Lu},
  booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2024},
  doi = {10.18653/v1/2024.acl-long.292},
  url = {https://doi.org/10.18653/v1/2024.acl-long.292}
}

References

78 references, 35 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609.
  2. Anton Bakhtin, Noam Brown, Emily Dinan, Gabriele Farina, Colin Flaherty, Daniel Fried, Andrew Goff, Jonathan Gray, Hengyuan Hu, Athul Paul Jacob, Mojtaba Komeili, Karthik Konath, Minae Kwon, Adam Lerer, Mike Lewis, Alexander H. Miller, Sandra Mitts, Adithya Renduchintala, Stephen Roller, Dirk Rowe,… find
  3. Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Michal Podstawski, Hubert Niewiadomski, Piotr Nyczyk, et al. 2023. Graph of thoughts: Solving elaborate problems with large language models. arXiv preprint arXiv:2308.09687. find
  4. Yao Fu, Hao-Chun Peng, Tushar Khot, and Mirella Lapata. 2023. Improving language model negotiation with self-play and in-context learning from ai feedback. ArXiv, abs/2305.10142.
  5. Ethan Brooks, Logan A Walls, Richard Lewis, and Satinder Singh. 2023. Large language models can implement policy iteration. In Thirty-seventh Conference on Neural Information Processing Systems. find
  6. Ran Gong, Qiuyuan Huang, Xiaojian Ma, Hoi Vo, Zane Durante, Yusuke Noda, Zilong Zheng, Song-Chun Zhu, Demetri Terzopoulos, Li Fei-Fei, et al. 2023. Mindagent: Emergent gaming interaction. arXiv preprint arXiv:2309.09971. find
  7. Kranti Chalamalasetti, Jana Götze, Sherzod Hakimov, Brielen Madureira, Philipp Sadler, and David Schlangen. 2023. clembench: Using game play to evaluate chat-optimized language models as conversational agents. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing,… find
  8. Liting Chen, Lu Wang, Hang Dong, Yali Du, Jie Yan, Fangkai Yang, Shuang Li, Pu Zhao, Si Qin, Saravan Rajmohan, et al. 2023a. Introspective tips: Large language model for in-context decision making. arXiv preprint arXiv:2305.11598. — [arXiv:2305.11598](https://arxiv.org/abs/2305.11598) find
  9. Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Cheng Qian, Chi-Min Chan, Yujia Qin, Ya-Ting Lu, Ruobing Xie, Zhiyuan Liu, Maosong Sun, and Jie Zhou. 2023b. Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors in agents. ArXiv, abs/2308.10848.
  10. Zixiang Chen, Yihe Deng, Huizhuo Yuan, Kaixuan Ji, and Quanquan Gu. 2024. Self-play fine-tuning converts weak language models to strong language models. arXiv preprint arXiv:2401.01335. find
  11. Jiale Cheng, Xiao Liu, Kehan Zheng, Pei Ke, Hongning Wang, Yuxiao Dong, Jie Tang, and Minlie Huang. 2023. Black-box prompt optimization: Aligning large language models without model training. arXiv preprint arXiv:2311.04155.
  12. Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, and others. 2022. Palm: Scaling language modeling with pathways. ArXiv, abs/2204.02311.
  13. Yilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum, and Igor Mordatch. 2023. Improving factuality and reasoning in language models through multiagent debate. ArXiv, abs/2305.14325.
  14. Zane Durante, Bidipta Sarkar, Ran Gong, Rohan Taori, Yusuke Noda, Paul Tang, Ehsan Adeli, Shrinidhi Kowshika Lakshmikanth, Kevin Schulman, Arnold Milstein, et al. 2024. An interactive agent foundation model. arXiv preprint arXiv:2402.05929. — [arXiv:2402.05929](https://arxiv.org/abs/2402.05929) find
  15. Caoyun Fan, Jindou Chen, Yaohui Jin, and Hao He. 2023. Can large language models serve as rational players in game theory? a systematic analysis. arXiv preprint arXiv:2312.05488. — [arXiv:2312.05488](https://arxiv.org/abs/2312.05488) find
  16. Jiaxian Guo, Bo Yang, Paul Yoo, Bill Yuchen Lin, Yusuke Iwasawa, and Yutaka Matsuo. 2023a. Suspicion-agent: Playing imperfect information games with theory of mind aware gpt-4. arXiv preprint arXiv:2309.17277. — [arXiv:2309.17277](https://arxiv.org/abs/2309.17277) find
  17. Qingyan Guo, Rui Wang, Junliang Guo, Bei Li, Kaitao Song, Xu Tan, Guoqing Liu, Jiang Bian, and Yujiu Yang. 2023b. Connecting large language models with evolutionary algorithms yields powerful prompt optimizers. arXiv preprint arXiv:2309.08532. find
  18. Sirui Hong, Xiawu Zheng, Jonathan P. Chen, Yuheng Cheng, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zi Hen Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, and Chenglin Wu. 2023. Metagpt: Meta programming for multi-agent collaborative framework. ArXiv, abs/2308.00352.
  19. Cho-Jui Hsieh, Si Si, Felix X Yu, and Inderjit S Dhillon. 2023. Automatic engineering of long prompts. arXiv preprint arXiv:2311.10117. find
  20. Jiaxin Huang, Shixiang Shane Gu, Le Hou, Yuexin Wu, Xuezhi Wang, Hongkun Yu, and Jiawei Han. 2022. Large language models can self-improve. ArXiv, abs/2210.11610.
  21. Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023a. Camel: Communicative agents for "mind" exploration of large language model society. In Thirty-seventh Conference on Neural Information Processing Systems.
  22. Huao Li, Yu Chong, Simon Stepputtis, Joseph Campbell, Dana Hughes, Charles Lewis, and Katia Sycara. 2023b. Theory of mind for multi-agent collaboration via large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 180–192, Singapore. Asso…
  23. Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, Shudan Zhang, Xiang Deng, Aohan Zeng, Zhengxiao Du, Chenhui Zhang, Sheng Shen, Tianjun Zhang, Yu Su, Huan Sun, Minlie Huang, Yuxiao Dong, and Jie Tang. 2023. Agentbench: Evaluating llms…
  24. Nunzio Lorè and Babak Heydari. 2023. Strategic behavior of large language models: Game structure vs. contextual framing. arXiv preprint arXiv:2309.05898. — [arXiv:2309.05898](https://arxiv.org/abs/2309.05898) find
  25. Weiyu Ma, Qirui Mi, Xue Yan, Yuqiao Wu, Runji Lin, Haifeng Zhang, and Jun Wang. 2023. Large language models play starcraft ii: Benchmarks and a chain of summarization approach. arXiv preprint arXiv:2312.11865. — [arXiv:2312.11865](https://arxiv.org/abs/2312.11865) find
  26. Yaxi Lu, Weilin Zhao, Yuxiang Huang, Junxi Yan, Xu Han, Xian Sun, Dahai Li, Jason Phang, Cheng Yang, Tongshuang Wu, Heng Ji, Zhiyuan Liu, and Maosong Sun. 2023a. Tool learning with foundation models.
  27. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Sean Welleck, Bodhisattwa Prasad Majumder, Shashank Gupta, Amir Yazdanbakhsh, and Peter Clark. 2023. Self-refine: Iterative refinement with self-feedback. ArX… find
  28. Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, et al. 2023b. Toolllm: Facilitating large language models to master 16000+ real-world apis. arXiv preprint arXiv:2307.16789.
  29. 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. 2015. Human-level control through deep reinforcement learning. nature, 518(7540):529–533. find
  30. OpenAI. 2023. Gpt-4 technical report.
  31. Liangming Pan, Michael Stephen Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang, and William Yang Wang. 2023. Automatically correcting large language models: Surveying the landscape of diverse self-correction strategies. ArXiv, abs/2308.03188. find
  32. Joon Sung Park, Joseph C. O’Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, and Michael S. Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In In the 36th Annual ACM Symposium on User Interface Software and Technology (UIST ’23), UIST ’23, New York, NY, USA. As… find
  33. Debjit Paul, Mete Ismayilzada, Maxime Peyrard, Beatriz Borges, Antoine Bosselut, Robert West, and Boi Faltings. 2023. Refiner: Reasoning feedback on intermediate representations. ArXiv, abs/2304.01904.
  34. David Premack and Guy Woodruff. 1978. Does the chimpanzee have a theory of mind? Behavioral and brain sciences, 1(4):515–526. find
  35. Reid Pryzant, Dan Iter, Jerry Li, Yin Tat Lee, Chenguang Zhu, and Michael Zeng. 2023. Automatic prompt optimization with" gradient descent" and beam search. arXiv preprint arXiv:2305.03495.
  36. Cheng Qian, Shihao Liang, Yujia Qin, Yining Ye, Xin Cong, Yankai Lin, Yesai Wu, Zhiyuan Liu, and Maosong Sun. 2024. Investigate-consolidate-exploit: A general strategy for inter-task agent self-evolution. arXiv preprint arXiv:2401.13996. — [arXiv:2401.13996](https://arxiv.org/abs/2401.13996) find
  37. Yujia Qin, Shengding Hu, Yankai Lin, Weize Chen, Ning Ding, Ganqu Cui, Zheni Zeng, Yufei Huang, Chaojun Xiao, Chi Han, Yi Ren Fung, Yusheng Su, Huadong Wang, Cheng Qian, Runchu Tian, Kunlun Zhu, Shihao Liang, Xingyu Shen, Bokai Xu, Zhen Zhang, Yining Ye, Bowen Li, Ziwei Tang, Jing Yi, Yuzhang Zhu, Z… — Toolformer: Language Models Can Teach Themselves to Use Tools
  38. Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, and Yueting Zhuang. 2023a. Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face. In Advances in Neural Information Processing Systems.
  39. Yongliang Shen, Kaitao Song, Xu Tan, Wenqi Zhang, Kan Ren, Siyu Yuan, Weiming Lu, Dongsheng Li, and Yueting Zhuang. 2023b. Taskbench: Benchmarking large language models for task automation. arXiv preprint arXiv:2311.18760. — [arXiv:2311.18760](https://arxiv.org/abs/2311.18760) find
  40. Noah Shinn, Beck Labash, and Ashwin Gopinath. 2023. Reflexion: an autonomous agent with dynamic memory and self-reflection. ArXiv, abs/2303.11366.
  41. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aur’elien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023a. Llama: Open and Efficient Foundation Language Models. ArXiv,…
  42. Hugo Touvron, Louis Martin, Kevin R. Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Daniel M. Bikel, Lukas Blecher, Cristian Cantón Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Bria… — Llama 2: Open Foundation and Fine-Tuned Chat Models
  43. Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2023a. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291. find
  44. Shenzhi Wang, Chang Liu, Zilong Zheng, Siyuan Qi, Shuo Chen, Qisen Yang, Andrew Zhao, Chaofei Wang, Shiji Song, and Gao Huang. 2023b. Avalon’s game of thoughts: Battle against deception through recursive contemplation. arXiv preprint arXiv:2310.01320. — [arXiv:2310.01320](https://arxiv.org/abs/2310.01320) find
  45. Xinyuan Wang, Chenxi Li, Zhen Wang, Fan Bai, Haotian Luo, Jiayou Zhang, Nebojsa Jojic, Eric P Xing, and Zhiting Hu. 2023c. Promptagent: Strategic planning with language models enables expert-level prompt optimization. arXiv preprint arXiv:2310.16427. find
  46. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Huai hsin Chi, and Denny Zhou. 2022. Self-consistency improves chain of thought reasoning in language models. ArXiv, abs/2203.11171.
  47. Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H. Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus. 2022a. Emergent abilities of large language models. CoRR, abs/2206.07…
  48. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed Chi, Quoc V Le, and Denny Zhou. 2022b. Chain of Thought Prompting Elicits Reasoning in Large Language Models. In Conference on Neural Information Processing Systems (NeurIPS).
  49. Chenfei Wu, Shengming Yin, Weizhen Qi, Xiaodong Wang, Zecheng Tang, and Nan Duan. 2023a. Visual chatgpt: Talking, drawing and editing with visual foundation models. arXiv preprint arXiv:2303.04671.
  50. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, and Chi Wang. 2023b. Autogen: Enabling next-gen llm applications via multi-agent conversation framework. ArXiv, abs/2308.08155.
  51. Yiquan Wu, Kun Kuang, Yating Zhang, Xiaozhong Liu, Changlong Sun, Jun Xiao, Yueting Zhuang, Luo Si, and Fei Wu. 2020. De-biased court’s view generation with causality. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 763–780. find
  52. Yiquan Wu, Yifei Liu, Weiming Lu, Yating Zhang, Jun Feng, Changlong Sun, Fei Wu, and Kun Kuang. 2022. Towards interactivity and interpretability: A rationale-based legal judgment prediction framework. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 47… find
  53. Yiquan Wu, Yifei Liu, Ziyu Zhao, Weiming Lu, Yating Zhang, Changlong Sun, Fei Wu, and Kun Kuang. 2024. De-biased attention supervision for text classification with causality. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 19279–19287. find
  54. Yiquan Wu, Siying Zhou, Yifei Liu, Weiming Lu, Xiaozhong Liu, Yating Zhang, Changlong Sun, Fei Wu, and Kun Kuang. 2023c. Precedent-enhanced legal judgment prediction with llm and domain-model collaboration. arXiv preprint arXiv:2310.09241. find
  55. Yue Wu, Xuan Tang, Tom M Mitchell, and Yuanzhi Li. 2023d. Smartplay: A benchmark for llms as intelligent agents. arXiv preprint arXiv:2310.01557. find
  56. Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, et al. 2023. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864.
  57. Yuzhuang Xu, Shuo Wang, Peng Li, Fuwen Luo, Xiaolong Wang, Weidong Liu, and Yang Liu. 2023a. Exploring large language models for communication games: An empirical study on werewolf. arXiv preprint arXiv:2309.04658.
  58. Zelai Xu, Chao Yu, Fei Fang, Yu Wang, and Yi Wu. 2023b. Language agents with reinforcement learning for strategic play in the werewolf game. arXiv preprint arXiv:2310.18940. — [arXiv:2310.18940](https://arxiv.org/abs/2310.18940) find
  59. Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V Le, Denny Zhou, and Xinyun Chen. 2023. Large language models as optimizers. arXiv preprint arXiv:2309.03409.
  60. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. ArXiv, abs/2305.10601. find
  61. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. ArXiv, abs/2210.03629.
  62. Qinyuan Ye, Maxamed Axmed, Reid Pryzant, and Fereshte Khani. 2023. Prompt engineering a prompt engineer. arXiv preprint arXiv:2311.05661. find
  63. Aohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang, Hanyu Lai, Ming Ding, Zhuoyi Yang, Yifan Xu, Wendi Zheng, Xiao Xia, Weng Lam Tam, Zixuan Ma, Yufei Xue, Jidong Zhai, Wenguang Chen, Zhiyuan Liu, Peng Zhang, Yuxiao Dong, and Jie Tang. 2023. Glm-130b: An Open Bilingual Pre-trained Model.
  64. Daochen Zha, Kwei-Herng Lai, Yuanpu Cao, Songyi Huang, Ruzhe Wei, Junyu Guo, and Xia Hu. 2019. Rlcard: A toolkit for reinforcement learning in card games. arXiv preprint arXiv:1910.04376. — [arXiv:1910.04376](https://arxiv.org/abs/1910.04376) find
  65. Daochen Zha, Jingru Xie, Wenye Ma, Sheng Zhang, Xiangru Lian, Xia Hu, and Ji Liu. 2021. Douzero: Mastering doudizhu with self-play deep reinforcement learning. In international conference on machine learning, pages 12333–12344. PMLR. find
  66. Ceyao Zhang, Kaijie Yang, Siyi Hu, Zihao Wang, Guanghe Li, Yihang Sun, Cheng Zhang, Zhaowei Zhang, Anji Liu, Song-Chun Zhu, et al. 2023a. Proagent: Building proactive cooperative ai with large language models. arXiv preprint arXiv:2308.11339. — [arXiv:2308.11339](https://arxiv.org/abs/2308.11339) find
  67. Chi Zhang, Zhao Yang, Jiaxuan Liu, Yucheng Han, Xin Chen, Zebiao Huang, Bin Fu, and Gang Yu. 2023b. Appagent: Multimodal agents as smartphone users. find
  68. Danyang Zhang, Lu Chen, Situo Zhang, Hongshen Xu, Zihan Zhao, and Kai Yu. 2023c. Large language model is semi-parametric reinforcement learning agent. arXiv preprint arXiv:2306.07929. — [arXiv:2306.07929](https://arxiv.org/abs/2306.07929) find
  69. Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. 2022a. Opt: Open Pre-tra…
  70. Wenqi Zhang, Kai Zhao, Peng Li, Xiaochun Zhu, Fap-ing Ye, Wei Jiang, Huiqiao Fu, and Tao Wang. 2021. Learning to navigate in a vuca environment: Hierarchical multi-expert approach. 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 9254–9261. find
  71. Andrew Zhao, Daniel Huang, Quentin Xu, Matthieu Lin, Yong-Jin Liu, and Gao Huang. 2023. Expel: Llm agents are experiential learners. arXiv preprint arXiv:2308.10144. find
  72. Denny Zhou, Nathanael Scharli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Olivier Bousquet, Quoc Le, and Ed Huai hsin Chi. 2022a. Least-to-most prompting enables complex reasoning in large language models. ArXiv, abs/2205.10625.
  73. Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. 2022b. Large language models are human-level prompt engineers. arXiv preprint arXiv:2211.01910.
  74. Wenqi Zhang, Yongliang Shen, Weiming Lu, and Yueting Zhuang. 2023d. Data-copilot: Bridging billions of data and humans with autonomous workflow. arXiv preprint arXiv:2306.07209. — [arXiv:2306.07209](https://arxiv.org/abs/2306.07209) find
  75. Wenqi Zhang, Yongliang Shen, Yanna Ma, Xiaoxia Cheng, Zeqi Tan, Qingpeng Nong, and Weiming Lu. 2022b. Multi-view reasoning: Consistent contrastive learning for math word problem. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 1103–1116. find
  76. Wenqi Zhang, Yongliang Shen, Qingpeng Nong, Zeqi Tan, Yanna Ma, and Weiming Lu. 2023e. An expression tree decoding strategy for mathematical equation generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 439–456, Singapore. Association for Compu… find
  77. Wenqi Zhang, Yongliang Shen, Linjuan Wu, Qiuying Peng, Jun Wang, Yueting Zhuang, and Weiming Lu. 2024. Self-contrast: Better reflection through inconsistent solving perspectives. arXiv preprint arXiv:2401.02009.
  78. Wenqi Zhang, Kai Zhao, Peng Li, Xiao Zhu, Yongliang Shen, Yanna Ma, Yingfeng Chen, and Weiming Lu. 2022c. A closed-loop perception, decision-making and reasoning mechanism for human-like navigation. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-2… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhang-2024-agent-pro-learning-evolve-policy/