[论文解读] Virtual Traffic Police: Large Language Model-Augmented Traffic Signal Control for Unforeseen Incidents

Shiqi Wei, Qiqing Wang+1 more|arXiv (Cornell University)|Jan 22, 2026

Traffic control and management被引用 0

一句话总结

本文提出一个层次化框架，在传统自适应交通信号控制（TSC）基础上加入基于大语言模型（LLM）的虚拟交通警察代理，利用检索增强的现有知识与自我 refinement 循环来应对突发交通事件。

ABSTRACT

Adaptive traffic signal control (TSC) has demonstrated strong effectiveness in managing dynamic traffic flows. However, conventional methods often struggle when unforeseen traffic incidents occur (e.g., accidents and road maintenance), which typically require labor-intensive and inefficient manual interventions by traffic police officers. Large Language Models (LLMs) appear to be a promising solution thanks to their remarkable reasoning and generalization capabilities. Nevertheless, existing works often propose to replace existing TSC systems with LLM-based systems, which can be (i) unreliable due to the inherent hallucinations of LLMs and (ii) costly due to the need for system replacement. To address the issues of existing works, we propose a hierarchical framework that augments existing TSC systems with LLMs, whereby a virtual traffic police agent at the upper level dynamically fine-tunes selected parameters of signal controllers at the lower level in response to real-time traffic incidents. To enhance domain-specific reliability in response to unforeseen traffic incidents, we devise a self-refined traffic language retrieval system (TLRS), whereby retrieval-augmented generation is employed to draw knowledge from a tailored traffic language database that encompasses traffic conditions and controller operation principles. Moreover, we devise an LLM-based verifier to update the TLRS continuously over the reasoning process. Our results show that LLMs can serve as trustworthy virtual traffic police officers that can adapt conventional TSC methods to unforeseen traffic incidents with significantly improved operational efficiency and reliability.

研究动机与目标

• 在传统基于模型的方法之外，动机在于为突发事件下的可靠交通信号控制提供需求
• 提出一个层次化的 LLM 增强 TSC 框架，高层 LLM 实时对下层控制器进行微调
• 通过 Traffic Language Retrieval System（TLRS）对 LLM 决策进行领域知识 grounding
• 引入自我 refinement 机制，让 LLM 作为生成器和验证者，持续改进 TLRS。

提出的方法

• 引入两级层次结构：上层 LLM 代理（虚拟交通警察）与下层自适应 TSC 控制器
• 使用零样本链路思维提示生成微调参数和推理轨迹
• 通过 TLRS grounding LLM 推理，从交通语言数据库中的事故-条件-控制链检索领域知识
• 实现基于 LLM 的验证器，对输出进行批评并更新 TLRS
• 展示最大压力控制与模型预测控制（MPC）控制器如何作为下层控制器集成并具有可调参数
• 将事故增强参数调优形式化为 GLLM(E_s)，以适应突发事件

实验结果

研究问题

• RQ1 RQ1 如何将传统 TSC 系统与 LLM Agents 结合以应对突发事件？
• RQ2 RQ2 通过领域 grounding 推理与自我 refinement，如何提升 LLM Agents 对交通事件的可靠性？

主要发现

• LLMs 可以作为可信的上层代理，将传统 TSC 方法适配到突发事件
• 以历史交通事故知识为 grounding 的 TLRS 提高了 LLM 决策的可靠性
• 自我 refinement 机制使 LLM 能批评自身输出并持续更新知识库
• 该框架在两种自适应 TSC 方法与四个仿真实例中进行评估，显示在运行效率和可靠性方面的改进（定性结论）