Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
51 tokens/sec
GPT-4o
60 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
8 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Cooperation on the Fly: Exploring Language Agents for Ad Hoc Teamwork in the Avalon Game (2312.17515v1)

Published 29 Dec 2023 in cs.CL

Abstract: Multi-agent collaboration with LLMs demonstrates proficiency in basic tasks, yet its efficiency in more complex scenarios remains unexplored. In gaming environments, these agents often face situations without established coordination protocols, requiring them to make intelligent inferences about teammates from limited data. This problem motivates the area of ad hoc teamwork, in which an agent may potentially cooperate with a variety of teammates to achieve a shared goal. Our study focuses on the ad hoc teamwork problem where the agent operates in an environment driven by natural language. Our findings reveal the potential of LLM agents in team collaboration, highlighting issues related to hallucinations in communication. To address this issue, we develop CodeAct, a general agent that equips LLM with enhanced memory and code-driven reasoning, enabling the repurposing of partial information for rapid adaptation to new teammates.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. Chateval: Towards better llm-based evaluators through multi-agent debate. arXiv preprint arXiv:2308.07201.
  2. Aateam: Achieving the ad hoc teamwork by employing the attention mechanism. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 7095–7102.
  3. Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors in agents. arXiv preprint arXiv:2308.10848.
  4. Teaching large language models to self-debug. arXiv preprint arXiv:2304.05128.
  5. Self-collaboration code generation via chatgpt. arXiv preprint arXiv:2304.07590.
  6. A review of cooperation in multi-agent learning. arXiv preprint arXiv:2312.05162.
  7. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352.
  8. Metatool benchmark for large language models: Deciding whether to use tools and which to use. arXiv preprint arXiv:2310.03128.
  9. Large language models are zero-shot reasoners. Advances in neural information processing systems, 35:22199–22213.
  10. Encouraging divergent thinking in large language models through multi-agent debate. arXiv preprint arXiv:2305.19118.
  11. Pecan: Leveraging policy ensemble for context-aware zero-shot human-ai coordination. In Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems(AAMAS), pages 679–688.
  12. Expected value of communication for planning in ad hoc teamwork. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 11290–11298.
  13. A survey of ad hoc teamwork: Definitions, methods, and open problems. In European Conference on Multiagent Systems.
  14. A penny for your thoughts: The value of communication in ad hoc teamwork. Good Systems-Published Research.
  15. R OpenAI. 2023. Gpt-4 technical report.
  16. Generative agents: Interactive simulacra of human behavior. arXiv preprint arXiv:2304.03442.
  17. Communicative agents for software development. arXiv preprint arXiv:2307.07924.
  18. Generating teammates for training robust ad hoc teamwork agents via best-response diversity. Transactions on Machine Learning Research.
  19. Towards open ad hoc teamwork using graph-based policy learning. In International Conference on Machine Learning, pages 8776–8786. PMLR.
  20. Stay moral and explore: Learn to behave morally in text-based games. In The Eleventh International Conference on Learning Representations.
  21. Self-imitation learning for action generation in text-based games. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 703–726.
  22. Reflexion: an autonomous agent with dynamic memory and self-reflection. arXiv preprint arXiv:2303.11366.
  23. Ad hoc autonomous agent teams: Collaboration without pre-coordination. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 1504–1509.
  24. A survey on large language model based autonomous agents. arXiv preprint arXiv:2308.11432.
  25. Augmenting language models with long-term memory. arXiv preprint arXiv:2306.07174.
  26. Unleashing cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration. arXiv preprint arXiv:2307.05300.
  27. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824–24837.
  28. Autogen: Enabling next-gen llm applications via multi-agent conversation framework. arXiv preprint arXiv:2308.08155.
  29. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864.
  30. Generalization in text-based games via hierarchical reinforcement learning. In Findings of the Association for Computational Linguistics: EMNLP 2021.
  31. Perceiving the world: Question-guided reinforcement learning for text-based games. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
  32. Deep reinforcement learning with stacked hierarchical attention for text-based games. Advances in Neural Information Processing Systems, 33:16495–16507.
  33. Exploring large language models for communication games: An empirical study on werewolf. arXiv preprint arXiv:2309.04658.
  34. An efficient end-to-end training approach for zero-shot human-ai coordination. In Thirty-seventh Conference on Neural Information Processing Systems.
  35. Tree of thoughts: Deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601.
  36. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629.
  37. How far are large language models from agents with theory-of-mind? arXiv preprint arXiv:2310.03051.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Zijing Shi (7 papers)
  2. Meng Fang (100 papers)
  3. Shunfeng Zheng (1 paper)
  4. Shilong Deng (5 papers)
  5. Ling Chen (144 papers)
  6. Yali Du (63 papers)
Citations (15)
View on Semantic Scholar