arXiv paper finds frontier LLM agents still struggle with zero-shot coordination in minimal environments
Zero-Shot Coordination among LLM Agents
The paper studies zero-shot coordination (ZSC) among LLM agents and finds that in deliberately simplified minimal environments, frontier LLM agents still struggle to coordinate. The main causes are their limited understanding of the coordination problem and weak reasoning about partners' beliefs. The authors propose coordination-friendly definitions (CFDs) as a way to enable stable coordination among LLM agents, and show that these definitions can be discovered automatically without human design; the code is released on GitHub.
The paper pinpoints the reasoning gaps behind frontier LLM agents' zero-shot coordination failures in minimal environments, and proposes coordination-friendly definitions that can be discovered automatically.
Source: arXiv Board & Classic Game AI · arxiv.org