# GameChat: Multi-LLM Dialogue for Safe, Agile, and Socially Optimal Multi-Agent Navigation in Constrained Environments

arXiv: https://arxiv.org/abs/2503.12333 · HTML: https://mlsanity.com/paper/2503.12333/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2025.

## Built on by (most cited first, 4 of 4)

- [A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?](https://mlsanity.com/paper/2505.10924/) (2025)
- [Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS](https://mlsanity.com/paper/2508.03125/) (2025)
- [CoopReflect: Towards Natural Language Communication for Cooperative Autonomous Driving via Multi-Agent Learning](https://mlsanity.com/paper/2505.18334/) (2025)
- [Prompt-Driven Domain Adaptation for End-to-End Autonomous Driving via In-Context RL](https://mlsanity.com/paper/2511.12755/) (2025)

## Abstract (arXiv)

Safe, agile, and socially compliant multi-robot navigation in cluttered and constrained environments remains a critical challenge. This is especially difficult with self-interested agents with unique, unknown priorities in decentralized settings, where there is no central authority to resolve conflicts induced by spatial symmetry. We address this challenge by proposing an intuitive, but very effective approach, GameChat, which facilitates safe, agile, and deadlock-free navigation for both cooperative and self-interested agents in cluttered environments. Key to our approach is the idea that agents should resolve conflicts on their own using natural language to communicate, much like humans. We evaluate GameChat in simulated environments with doorways and intersections. The results show that even in the worst case, GameChat reduces the time for all agents to reach their goals by over 35% from a naive baseline and by over 20% from a state of the art baseline in the intersection scenario, while doubling the rate of ensuring the agent with a higher priority task reaches the goal first, from 50% (equivalent to random chance) to 100%. We also demonstrate how GameChat can be extended to more than two agents.