LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models

• URL: http://arxiv.org/abs/2310.03903v2
• Date: Tue, 2 Apr 2024 22:35:39 GMT
• Title: LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models
• Authors: Saaket Agashe, Yue Fan, Anthony Reyna, Xin Eric Wang,
• Abstract summary: This study aims at a detailed analysis of Large Language Models (LLMs) within the context of Pure Coordination Games. Our findings indicate that LLM agents equipped with GPT-4-turbo achieve comparable performance to state-of-the-art reinforcement learning methods. Results on Coordination QA show a large room for improvement in the Theory of Mind reasoning and joint planning abilities of LLMs.
• Score: 23.092480882456048
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The emergent reasoning and Theory of Mind (ToM) abilities demonstrated by Large Language Models (LLMs) make them promising candidates for developing coordination agents. In this study, we introduce a new LLM-Coordination Benchmark aimed at a detailed analysis of LLMs within the context of Pure Coordination Games, where participating agents need to cooperate for the most gain. This benchmark evaluates LLMs through two distinct tasks: (1) \emph{Agentic Coordination}, where LLMs act as proactive participants for cooperation in 4 pure coordination games; (2) \emph{Coordination Question Answering (QA)}, where LLMs are prompted to answer 198 multiple-choice questions from the 4 games for evaluation of three key reasoning abilities: Environment Comprehension, ToM Reasoning, and Joint Planning. Furthermore, to enable LLMs for multi-agent coordination, we introduce a Cognitive Architecture for Coordination (CAC) framework that can easily integrate different LLMs as plug-and-play modules for pure coordination games. Our findings indicate that LLM agents equipped with GPT-4-turbo achieve comparable performance to state-of-the-art reinforcement learning methods in games that require commonsense actions based on the environment. Besides, zero-shot coordination experiments reveal that, unlike RL methods, LLM agents are robust to new unseen partners. However, results on Coordination QA show a large room for improvement in the Theory of Mind reasoning and joint planning abilities of LLMs. The analysis also sheds light on how the ability of LLMs to understand their environment and their partner's beliefs and intentions plays a part in their ability to plan for coordination. Our code is available at \url{https://github.com/eric-ai-lab/llm_coordination}.

Related papers

• Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information [36.11862095329315]
  Large language models (LLMs) have shown success in handling simple games with imperfect information. This study investigates the applicability of knowledge acquired by open-source and API-based LLMs to sophisticated text-based games.
  arXiv  Detail & Related papers  (2024-08-05T15:36:46Z)
• A Survey of Useful LLM Evaluation [20.048914787813263]
  Two-stage framework: from core ability'' to agent'' In the "core ability" stage, we discussed the reasoning ability, societal impact, and domain knowledge of LLMs. In the agent'' stage, we demonstrated embodied action, planning, and tool learning of LLMs agent applications.
  arXiv  Detail & Related papers  (2024-06-03T02:20:03Z)
• Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [70.09561665520043]
  We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans. We provide theoretical analysis by extending advantage-weighted regression in reinforcement learning to multi-agent systems. Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
  arXiv  Detail & Related papers  (2024-05-23T08:33:19Z)
• GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations [87.99872683336395]
  Large Language Models (LLMs) are integrated into critical real-world applications. This paper evaluates LLMs' reasoning abilities in competitive environments. We first propose GTBench, a language-driven environment composing 10 widely recognized tasks.
  arXiv  Detail & Related papers  (2024-02-19T18:23:36Z)
• MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration [102.41118020705876]
  Large Language Models (LLMs) have marked a significant advancement in the field of natural language processing. As their applications extend into multi-agent environments, a need has arisen for a comprehensive evaluation framework. This work introduces a novel benchmarking framework specifically tailored to assess LLMs within multi-agent settings.
  arXiv  Detail & Related papers  (2023-11-14T21:46:27Z)
• Theory of Mind for Multi-Agent Collaboration via Large Language Models [5.2767999863286645]
  This study evaluates Large Language Models (LLMs)-based agents in a multi-agent cooperative text game with Theory of Mind (ToM) inference tasks. We observed evidence of emergent collaborative behaviors and high-order Theory of Mind capabilities among LLM-based agents.
  arXiv  Detail & Related papers  (2023-10-16T07:51:19Z)
• Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation [52.930183136111864]
  We propose using scorable negotiation to evaluate Large Language Models (LLMs) To reach an agreement, agents must have strong arithmetic, inference, exploration, and planning capabilities. We provide procedures to create new games and increase games' difficulty to have an evolving benchmark.
  arXiv  Detail & Related papers  (2023-09-29T13:33:06Z)
• BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents [103.28404907655542]
  Large language models (LLMs) have led to the emerging exploration of Autonomous Agents (LAAs) This paper provides a comprehensive comparison of LAA in terms of both agent architectures and LLM backbones. We propose a new strategy to orchestrate multiple LAAs such that each labor LAA focuses on one type of action, textiti.e. BOLAA, where a controller manages the communication among multiple agents.
  arXiv  Detail & Related papers  (2023-08-11T06:37:54Z)
• Building Cooperative Embodied Agents Modularly with Large Language Models [104.57849816689559]
  We address challenging multi-agent cooperation problems with decentralized control, raw sensory observations, costly communication, and multi-objective tasks instantiated in various embodied environments. We harness the commonsense knowledge, reasoning ability, language comprehension, and text generation prowess of LLMs and seamlessly incorporate them into a cognitive-inspired modular framework. Our experiments on C-WAH and TDW-MAT demonstrate that CoELA driven by GPT-4 can surpass strong planning-based methods and exhibit emergent effective communication.
  arXiv  Detail & Related papers  (2023-07-05T17:59:27Z)
• Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate [41.949869545423375]
  Large Language Models (LLMs) have shown impressive capabilities in various applications, but they still face various inconsistency issues. To examine whether LLMs can collaborate effectively to achieve a consensus for a shared goal, we focus on commonsense reasoning. Our work contributes to understanding the inter-consistency among LLMs and lays the foundation for developing future collaboration methods.
  arXiv  Detail & Related papers  (2023-05-19T11:15:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.