LangCoop: Collaborative Driving with Language

Multi-agent collaboration holds great promise for enhancing the safety, reliability, and mobility of autonomous driving systems by enabling information sharing among multiple connected agents. However, existing multi-agent communication approaches are hindered by limitations of existing communication media, including high bandwidth demands, agent heterogeneity, and information loss. To address these challenges, we introduce LangCoop, a new paradigm for collaborative autonomous driving that leverages natural language as a compact yet expressive medium for inter-agent communication. LangCoop features two key innovations: Mixture Model Modular Chain-of-thought (M$^3$CoT) for structured zero-shot vision-language reasoning and Natural Language Information Packaging (LangPack) for efficiently packaging information into concise, language-based messages. Through extensive experiments conducted in the CARLA simulations, we demonstrate that LangCoop achieves a remarkable 96\% reduction in communication bandwidth (< 2KB per message) compared to image-based communication, while maintaining competitive driving performance in the closed-loop evaluation. Our project page and code are atthis https URL.

@article{gao2025_2504.13406,
  title={ LangCoop: Collaborative Driving with Language },
  author={ Xiangbo Gao and Yuheng Wu and Rujia Wang and Chenxi Liu and Yang Zhou and Zhengzhong Tu },
  journal={arXiv preprint arXiv:2504.13406},
  year={ 2025 }
}