CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control

2025-03-14

AI Summary

Existing traffic signal control methods incorporating large language models (LLMs) lack explicit multi-agent coordination mechanisms, limiting their effectiveness in network-wide congestion mitigation. To address this, we propose a multi-agent LLM framework tailored for urban road networks. First, we construct a structured spatiotemporal graph to model dynamic interdependencies among intersections. Second, we design a complexity-aware dynamic chaining reasoning mechanism to enable distributed, adaptive decision-making across agents. Third, we introduce a simulation-driven lightweight LLM fine-tuning paradigm that balances collaborative performance and computational efficiency. Evaluated on both synthetic and real-world datasets, our approach significantly outperforms state-of-the-art methods, enabling real-time cooperative control across hundreds of intersections. It demonstrates strong generalization, scalability, and robustness under varying traffic conditions and infrastructure configurations.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Coordination and Collaboration
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Traffic Signal Control (TSC) plays a critical role in urban traffic management by optimizing traffic flow and mitigating congestion. While Large Language Models (LLMs) have recently emerged as promising tools for TSC due to their exceptional problem-solving and generalization capabilities, existing approaches fail to address the essential need for inter-agent coordination, limiting their effectiveness in achieving network-wide optimization. To bridge this gap, we propose CoLLMLight, a cooperative LLM agent framework for TSC. Specifically, we first construct a structured spatiotemporal graph to capture real-time traffic dynamics and spatial relationships among neighboring intersections, enabling the LLM to reason about complex traffic interactions. Moreover, we introduce a complexity-aware reasoning mechanism that dynamically adapts reasoning depth based on real-time traffic conditions, ensuring optimal computational efficiency without sacrificing decision quality. Besides, we propose a fine-tuning strategy that leverages iterative simulation-driven data collection and environmental feedback to build a lightweight LLM tailored for cooperative TSC. Extensive experiments on both synthetic and real-world datasets demonstrate that CoLLMLight outperforms state-of-the-art methods in diverse traffic scenarios, showcasing its effectiveness, scalability, and robustness.

Problem

• Addresses lack of inter-agent coordination in traffic signal control.
• Proposes a cooperative LLM framework for network-wide traffic optimization.
• Introduces adaptive reasoning and fine-tuning for efficient traffic management.

Innovation

• Cooperative LLM agents for traffic signal control
• Structured spatiotemporal graph captures traffic dynamics
• Complexity-aware reasoning adapts to real-time conditions