Cooperation on the Fly: Exploring Language Agents for Ad Hoc Teamwork in the Avalon Game

TL;DR

This paper investigates the use of Large Language Models as adaptable agents in ad hoc teamwork within natural language-driven environments, addressing communication hallucinations with a novel code-based reasoning approach.

Contribution

Introduces CodeAct, a new LLM-based agent with improved memory and reasoning capabilities for effective ad hoc teamwork in language-based settings.

Findings

LLM agents show potential in collaborative tasks

Communication hallucinations pose challenges in team coordination

CodeAct enhances adaptability and communication accuracy

Abstract

Multi-agent collaboration with Large Language Models (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.