LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay

2023/10/23 by Yihuai Lan, Zhiqiang Hu, Lan, Yihuai +15 · 9 citations
Business, Management and Accounting · Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #FinTech, Crowdfunding, Digital Finance #Mobile Agent-Based Network Management #Multi-Agent Systems and Negotiation

paper · pdf · doi:10.48550/arxiv.2310.14985

openalex publication_date 2023/10/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper explores the open research problem of understanding the social behaviors of LLM-based agents. Using Avalon as a testbed, we employ system prompts to guide LLM agents in gameplay. While previous studies have touched on gameplay with LLM agents, research on their social behaviors is lacking. We propose a novel framework, tailored for Avalon, features a multi-agent system facilitating efficient communication and interaction. We evaluate its performance based on game success and analyze LLM agents' social behaviors. Results affirm the framework's effectiveness in creating adaptive agents and suggest LLM-based agents' potential in navigating dynamic social interactions. By examining collaboration and confrontation behaviors, we offer insights into this field's research and applications. Our code is publicly available at https://github.com/3DAgentWorld/LLM-Game-Agent.

Cited by

• Beyond Single Plots: A Benchmark for Question Answering on Multi-Charts
• Prompt Governance? On Governing Technologies Governed by Natural Language
• Aligning Large Language Models with Procedural Rules: An Autoregressive State-Tracking Prompting for In-Game Trading
• Leading the Follower: Learning Persuasive Agents in Social Deduction Games
• The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems
• Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game
• What to Ask Next? Probing the Imaginative Reasoning of LLMs with TurtleSoup Puzzles
• The Roots of International Perceptions: Simulating US Attitude Changes Towards China with LLM Agents
• IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization

Related

• AvalonBench: Evaluating LLMs Playing the Game of Avalon
• Cultural Evolution of Cooperation among LLM Agents
• Do LLM Agents Exhibit Social Behavior?
• A Survey on Large Language Model-Based Game Agents
• Evolution of Cooperation in LLM-Agent Societies: A Preliminary Study Using Different Punishment Strategies