Traditional Reinforcement Learning (RL) suffers from replicating human-like behaviors, generalizing effectively in multi-agent scenarios, and overcoming inherent interpretabilitythis http URLtasks are compounded when deep environment understanding, agent coordination and dynamic optimization are required. While Large Language Model (LLM) enhanced methods have shown promise in generalization and interoperability, they often neglect necessary multi-agent coordination. Therefore, we introduce the Cascading Cooperative Multi-agent (CCMA) framework, integrating RL for individual interactions, a fine-tuned LLM for regional cooperation, a reward function for global optimization, and the Retrieval-augmented Generation mechanism to dynamically optimize decision-making across complex driving scenarios. Our experiments demonstrate that the CCMA outperforms existing RL methods, demonstrating significant improvements in both micro and macro-level performance in complex driving environments.
View on arXiv@article{zhang2025_2503.08199,
title={ A Cascading Cooperative Multi-agent Framework for On-ramp Merging Control Integrating Large Language Models },
author={ Miao Zhang and Zhenlong Fang and Tianyi Wang and Qian Zhang and Shuai Lu and Junfeng Jiao and Tianyu Shi },
journal={arXiv preprint arXiv:2503.08199},
year={ 2025 }
}