Deheng Ye

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

2023 · arXiv (Cornell University)

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 …

Reaching Consensus in Cooperative Multi-Agent Reinforcement Learning with Goal Imagination

2024 · arXiv (Cornell University)

Reaching consensus is key to multi-agent coordination. To accomplish a cooperative task, agents need to coherently select optimal joint actions to maximize the team reward. However, current cooperative multi-agent reinforcement learning (MARL) methods usually do …