A Cascading Cooperative Multi-agent Framework for On-ramp Merging Control Integrating Large Language Models
This addresses multi-agent coordination challenges in autonomous driving, though it appears incremental as it combines existing techniques (RL, LLMs) rather than introducing a fundamentally new approach.
The paper tackles the problem of traditional Reinforcement Learning's limitations in replicating human-like behaviors and coordinating effectively in multi-agent scenarios by introducing the Cascading Cooperative Multi-agent (CCMA) framework, which integrates RL, fine-tuned LLMs, and retrieval-augmented generation to achieve significant improvements in micro and macro-level performance in complex driving environments.
Traditional Reinforcement Learning (RL) suffers from replicating human-like behaviors, generalizing effectively in multi-agent scenarios, and overcoming inherent interpretability issues.These tasks 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.