ProAgent: Building Proactive Cooperative Agents with Large Language Models
Open accessAbstract
Building agents with adaptive behavior in cooperative tasks stands as a paramount goal in the realm of multi-agent systems. Current approaches to developing cooperative agents rely primarily on learning-based methods, whose policy generalization depends heavily on the diversity of teammates they interact with during the training phase. Such reliance, however, constrains the agents' capacity for strategic adaptation when cooperating with unfamiliar teammates, which becomes a significant challenge in zero-shot coordination scenarios. To address this challenge, we propose ProAgent, a novel framework that harnesses large language models (LLMs) to create proactive agents capable of dynamically adapting their behavior to enhance cooperation with teammates. ProAgent can analyze the present state, and infer the intentions of teammates from observations. It then updates its beliefs in alignment with the teammates' subsequent actual behaviors. Moreover, ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various of coordination scenarios. Experimental evaluations conducted within the Overcooked-AI environment unveil the remarkable performance superiority of ProAgent, outperforming five methods based on self-play and population-based training when cooperating with AI agents. Furthermore, in partnered with human proxy models, its performance exhibits an average improvement exceeding 10% compared to the current state-of-the-art method. For more information about our project, please visit https://pku-proagent.github.io.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
VillagerAgent (with GPT-4) surpasses ProAgent across all five Overcooked-AI scenarios: Cramped Room, Asymmetric Advantages, Coordination Ring, Forced Coordination, and Counter Circuit.
“our VillagerAgent (w/gpt-4), surpasses ProAgent (Zhang et al., 2024) across all five scenarios: Cramped Room, Asymmetric Advantages, Coordination Ring, Forced Coordination, and Counter Circuit.”
From VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft (2024) · cites this paper as Zhang et al., 2024
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208 · see citing works
Self-citationReflexion: Language Agents with Verbal Reinforcement Learning
Shinn, N., Cassano, F., Berman, E., Gopinath, A., Narasimhan, K., & Yao, S. (2023) · arXiv · doi:10.48550/arxiv.2303.11366 · Cited by 1,087 · cited 3× · see citing works
“Recent endeavors have translated LLMs’ reasoning capability into planning by constructing a monologue with feedback (Welleck et al. 2023; Shinn et al. 2023; Paul et al. 2023) to facilitate the reasoning and planning process.”
BackgroundMethodCode as Policies: Language Model Programs for Embodied Control
Liang, J., Huang, W., Xia, F., Xu, P., Hausman, K., Ichter, B., Florence, P., & Zeng, A. (2023) · 2023 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra48891.2023.10160591 · Cited by 767 · see citing works
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
Ahn, M., Brohan, A., Brown, N., Chebotar, Y., Cortes, O., David, B., Finn, C., Fu, C., Gopalakrishnan, K., Hausman, K., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.01691 · Cited by 624 · see citing works
Towards Reasoning in Large Language Models: A Survey
Huang, J., & Chang, K. C.-C. (2023) · Findings of the Association for Computational Linguistics: ACL 2023 · doi:10.18653/v1/2023.findings-acl.67 · Cited by 428 · see citing works
Reasoning with Language Model is Planning with World Model
Hao, S., Gu, Y., Ma, H., Hong, J., Wang, Z., Wang, D., & Hu, Z. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.507 · Cited by 168 · see citing works
Self-citationTrajectory Diversity for Zero-Shot Coordination
Lupu, A., Hu, H., & Foerster, J. (2021) · International Joint Conference on Autonomous Agents and Multiagent Systems · doi:10.65109/mfks7701 · Cited by 28 · see citing works
Flagged first, then by citations
Research works printed but not linked: 41
- Brown, T.; Mann, B.; Ryder, N.; Subbiah, M.; Kaplan, J. D.; Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; Askell, A.; et al. 2020. Language Models are Few-Shot Learners. In Advances in neural information processing systems, vol- ume 33, 1877-1901.
- Bubeck, S.; Chandrasekaran, V.; Eldan, R.; Gehrke, J.; Horvitz, E.; Kamar, E.; Lee, P.; Lee, Y. T.; Li, Y.; Lundberg, S.; Nori, H.; Palangi, H.; Ribeiro, M. T.; and Zhang, Y. 2023. Sparks of Artificial General Intelligence: Early Experiments with GPT-4. arXiv:2303.12712. · arXiv
- Carroll, M.; Shah, R.; Ho, M. K.; Griffiths, T.; Seshia, S.; Abbeel, P.; and Dragan, A. 2019. On the Utility of Learning about Humans for Human-AI Coordination. In Advances in neural information processing systems, volume 32.
- Ding, Z.; Zhang, W.; Yue, J.; Wang, X.; Huang, T.; and Lu, Z. 2023. Entity Divider with Language Grounding in Multi- Agent Reinforcement Learning. In International Conference on Machine Learning, 8103-8119.
- PMLR.
- Du, Y.; Watkins, O.; Wang, Z.; Colas, C.; Darrell, T.; Abbeel, P.; Gupta, A.; and Andreas, J. 2023. Guiding Pre- training in Reinforcement Learning with Large Language Models. arXiv:2302.06692. · arXiv
- Fan, L.; Wang, G.; Jiang, Y.; Mandlekar, A.; Yang, Y.; Zhu, H.; Tang, A.; Huang, D.-A.; Zhu, Y.; and Anandkumar, A. 2022. MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge. In NIPS Processing Systems Datasets and Benchmarks Track.
- PMLR.
- Hu, H.; and Foerster, J. N. 2020. Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning. In Interna- tional Conference on Learning Representations.
- PMLR.
- Hu, H.; and Sadigh, D. 2023. Language Instructed Rein- forcement Learning for Human-AI Coordination. In Pro- ceedings of the 40th International Conference on Machine Learning. PMLR.
- Hu, S.; Zhu, F.; Chang, X.; and Liang, X. 2021b. UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers. arXiv:2101.08001. · arXiv
- Jaderberg, M.; Dalibard, V.; Osindero, S.; Czarnecki, W. M.; Donahue, J.; Razavi, A.; Vinyals, O.; Green, T.; Dun- ning, I.; Simonyan, K.; Fernando, C.; and Kavukcuoglu, K. 2017. Population Based Training of Neural Networks. arXiv:1711.09846. · arXiv
- Kojima, T.; Gu, S. S.; Reid, M.; Matsuo, Y.; and Iwasawa, Y. 2022. Large Language Models are Zero-Shot Reasoners. In Advances in neural information processing systems, vol- ume 35, 22199-22213.
- Li, W.; Qiao, D.; Wang, B.; Wang, X.; Jin, B.; and Zha, H. 2023a. Semantically Aligned Task Decomposition in Multi- Agent Reinforcement Learning. arXiv:2305.10865. · arXiv
- Li, Y.; Zhang, S.; Sun, J.; Du, Y.; Wen, Y.; Wang, X.; and Pan, W. 2023b. Cooperative Open-ended Learning Frame- work for Zero-shot Coordination. In Proceedings of the 40th International Conference on Machine Learning. PMLR.
- Li, Y.; Zhang, S.; Sun, J.; Zhang, W.; Du, Y.; Wen, Y.; Wang, X.; and Pan, W. 2024. Tackling Cooperative Incompatibility for Zero-Shot Human-AI Coordination. arXiv:2306.03034. · arXiv
- PMLR.
- Meng, L.; Wen, M.; Yang, Y.; Le, C.; Li, X.; Zhang, W.; Wen, Y.; Zhang, H.; Wang, J.; and Xu, B. 2022. Offline Pre-trained Multi-Agent Decision Transformer: One Big Se- quence Model Tackles All SMAC Tasks. arXiv:2112.02845. · arXiv
- Mialon, G.; Dessì, R.; Lomeli, M.; Nalmpantis, C.; Pa- sunuru, R.; Raileanu, R.; Rozière, B.; Schick, T.; Dwivedi- Yu, J.; Celikyilmaz, A.; Grave, E.; LeCun, Y.; and Scialom, T. 2023. Augmented Language Models: a Survey. arXiv:2302.07842. · arXiv
- Paul, D.; Ismayilzada, M.; Peyrard, M.; Borges, B.; Bosselut, A.; West, R.; and Faltings, B. 2023. RE- FINER: Reasoning Feedback on Intermediate Representa- tions. arXiv:2304.01904. · arXiv
- Rashid, T.; Samvelyan, M.; Schroeder, C.; Farquhar, G.; Fo- erster, J.; and Whiteson, S. 2018. QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning. In International Conference on Machine Learn- ing, 4295-4304.
- PMLR.
- Singh, I.; Blukis, V.; Mousavian, A.; Goyal, A.; Xu, D.; Tremblay, J.; Fox, D.; Thomason, J.; and Garg, A. 2023. ProgPrompt: Generating Situated Robot Task Plans using Large Language Models. In 2023 IEEE International Con- ference on Robotics and Automation (ICRA), 11523-11530.
- Strouse, D.; McKee, K.; Botvinick, M.; Hughes, E.; and Ev- erett, R. 2021. Collaborating with Humans without Human Data. In Advances in Neural Information Processing Sys- tems, volume 34, 14502-14515.
- Tesauro, G. 1994. TD-Gammon, a self-teaching backgam- mon program, achieves master-level play. Neural computa- tion, 6(2): 215-219.
- Wang, X.; Wei, J.; Schuurmans, D.; Le, Q. V.; Chi, E. H.; Narang, S.; Chowdhery, A.; and Zhou, D. 2023a. Self- Consistency Improves Chain of Thought Reasoning in Lan- guage Models. In The Eleventh International Conference on Learning Representations.
- Wang, Y.; Zhong, F.; Xu, J.; and Wang, Y. 2021. ToM2C: Target-oriented Multi-agent Communication and Coopera- tion with Theory of Mind. In International Conference on Learning Representations.
- Wang, Z.; Cai, S.; Chen, G.; Liu, A.; Ma, X.; and Liang, Y. 2023b. Describe, Explain, Plan and Select: Interactive Plan- ning with LLMs Enables Open-World Multi-Task Agents. In Thirty-seventh Conference on Neural Information Process- ing Systems.
- Wang, Z.; Cai, S.; Liu, A.; Jin, Y.; Hou, J.; Zhang, B.; Lin, H.; He, Z.; Zheng, Z.; Yang, Y.; Ma, X.; and Liang, Y. 2023c. JARVIS-1: Open-World Multi-Task Agents with Memory-Augmented Multimodal Language Models. arXiv:2311.05997. · arXiv
- Wei, J.; Wang, X.; Schuurmans, D.; Bosma, M.; brian ichter; Xia, F.; Chi, E. H.; Le, Q. V.; and Zhou, D. 2022. Chain of Thought Prompting Elicits Reasoning in Large Language Models. In Advances in Neural Information Processing Sys- tems, volume 35, 24824-24837.
- Welleck, S.; Lu, X.; West, P.; Brahman, F.; Shen, T.; Khashabi, D.; and Choi, Y. 2023. Generating Sequences by Learning to Self-Correct. In The Eleventh International Conference on Learning Representations.
- Wen, M.; Kuba, J.; Lin, R.; Zhang, W.; Wen, Y.; Wang, J.; and Yang, Y. 2022. Multi-Agent Reinforcement Learning is a Sequence Modeling Problem. In Advances in Neural Information Processing Systems, volume 35, 16509-16521.
- Wu, S. A.; Wang, R. E.; Evans, J. A.; Tenenbaum, J. B.; Parkes, D. C.; and Kleiman-Weiner, M. 2021. Too Many Cooks: Bayesian Inference for Coordinating Multi-Agent Collaboration. Topics in Cognitive Science, 13(2): 414-432.
- Yang, Y.; and Wang, J. 2021. An Overview of Multi-Agent Reinforcement Learning from Game Theoretical Perspec- tive. arXiv:2011.00583. · arXiv
- Yao, S.; Zhao, J.; Yu, D.; Du, N.; Shafran, I.; Narasimhan, K. R.; and Cao, Y. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. In The Eleventh International Conference on Learning Representations.
- Yu, C.; Velu, A.; Vinitsky, E.; Gao, J.; Wang, Y.; Bayen, A.; and Wu, Y. 2022. The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games. In Advances in Neural In- formation Processing Systems, volume 35, 24611-24624.
- Zhang, H.; Du, W.; Shan, J.; Zhou, Q.; Du, Y.; Tenenbaum, J. B.; Shu, T.; and Gan, C. 2023. Building Cooperative Embodied Agents Modularly with Large Language Models. arXiv:2307.02485. · arXiv
- Zhao, R.; Song, J.; Yuan, Y.; Hu, H.; Gao, Y.; Wu, Y.; Sun, Z.; and Yang, W. 2023. Maximum Entropy Popula- tion Based Training for Zero-Shot Human-AI Coordination. In Proceedings of the AAAI Conference on Artificial Intelli- gence, 5, 6145-6153.
- Zhong, Y.; Kuba, J. G.; Feng, X.; Hu, S.; Ji, J.; and Yang, Y. 2023. Heterogeneous-Agent Reinforcement Learning. arXiv:2304.09870. · arXiv
- Zhou, D.; Schärli, N.; Hou, L.; Wei, J.; Scales, N.; Wang, X.; Schuurmans, D.; Cui, C.; Bousquet, O.; Le, Q. V.; and Chi, E. H. 2023. Least-to-Most Prompting Enables Com- plex Reasoning in Large Language Models. In The Eleventh International Conference on Learning Representations.
Cited by
Sorted by citations
A survey on large language model based autonomous agents
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2024) · Frontiers of Computer Science · doi:10.1007/s11704-024-40231-1 · Cited by 1,941 · see citing works
Self-citationA survey on LLM-based multi-agent systems: Workflow, infrastructure, and challenges
Li, X., Wang, S., Zeng, S., Wu, Y., & Yang, Y. (2024) · Vicinagearth · doi:10.1007/s44336-024-00009-2 · Cited by 404 · see citing works
Self-citationGenerative AI for self-adaptive systems: State of the art and research roadmap
Li, J., Zhang, M., Li, N., Weyns, D., Jin, Z., & Tei, K. (2024) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/3686803 · Cited by 77 · see citing works
<b>JARVIS</b> -1: Open-World Multi-Task Agents With Memory-Augmented Multimodal Language Models
Wang, Z., Cai, S., Liu, A., Jin, Y., Hou, J., Zhang, B., Lin, H., He, Z., Zheng, Z., Yang, Y., et al. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3511593 · Cited by 36 · see citing works
“There have been some methods leveraging the large language model to generate action plans for high-level tasks in embodied environments [55, 12, 34, 33, 56, 57, 16].”
Self-citationMulti-Agent Collaboration Mechanisms: A Survey of LLMs
Tran, K.-T., Dao, D., Nguyen, M.-D., Pham, Q.-V., O'Sullivan, B., & Nguyen, H. D. (2025) · arXiv · doi:10.48550/arxiv.2501.06322 · Cited by 26 · see citing works
DAWN: Designing Distributed Agents in a Worldwide Network
Aminiranjbar, Z., Tang, J., Wang, Q., Pant, S., & Viswanathan, M. (2024) · arXiv · doi:10.48550/arxiv.2410.22339 · Cited by 8 · see citing works
Dong, Y., Zhu, X., Pan, Z., Zhu, L., & Yang, Y. (2024) · Findings of the Association for Computational Linguistics ACL 2024 · doi:10.18653/v1/2024.findings-acl.964 · Cited by 13 · see citing works
Self-citationDroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving
Liu, Y., Huang, Y., Yao, J., Feng, S., Gu, Z., Du, K., Li, H., Cheng, Y., Jiang, J., Lu, S., et al. (2024) · arXiv · doi:10.48550/arxiv.2411.02820 · Cited by 2 · see citing works
Gómez Álvarez, S., Mozo Quesada, A., Navarro, T., Gálvez Rojas, S., & López Valverde, F. (2026) · Journal of Intelligent Information Systems · doi:10.1007/s10844-026-01086-z
Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
Du, P. (2026) · arXiv · Cited by 1 · see citing works
“ProAgent [Zhang et al., 2024b] builds proactive teammates that anticipate needs based on memory of past interactions.”
Lyfe Agents: Generative agents for low-cost real-time social interactions
Kaiya, Z., Naim, M., Kondic, J., Cortes, M., Ge, J., Luo, S., Yang, G. R., & Ahn, A. (2023) · arXiv · doi:10.48550/arxiv.2310.02172 · Cited by 2 · see citing works
- Authors
- Zhang, C., Yang, K., Hu, S., Wang, Z., Li, G., Sun, Y., Zhang, C., Zhang, Z., Liu, A., Zhu, S.-C., Chang, X., Zhang, J., Yin, F., Liang, Y., & Yang, Y.
- Affiliations
- Peking University (CN)
- Chinese Academy of Sciences (CN)
- University of Technology Sydney (AU)
- Beijing Institute for General Artificial Intelligence (CN)
- Chinese University of Hong Kong, Shenzhen (CN)
- ORCID
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2024-03-24
- Volume
- 38
- Issue
- 16
- Pages
- 17591-17599
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W4393147219
- Cited by
- 88
- References
- 7
- Citations by year
- 2026: 34 · 2025: 34 · 2024: 20
- FWCI
- 21.27
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62376013, ZDSYS201707251409055, [2020]-02, 62271433, 2017ZT07X152)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
- Keywords
- multi-agent systems, large language models, belief updating, adaptive behavior, human-AI collaboration, interpretability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
