用大模型生成可解释的交通信号控制策略，兼顾效果与人工可读性。
SignalClaw: LLM-Guided Evolutionary Synthesis of Interpretable Traffic Signal Control Skills
- 用大语言模型生成带理由和代码的可解释控制技能，支持进化优化。
- 常规场景下平均延迟7.8–9.2秒，事件场景下应急车延迟降至11.2–18.5秒。
- 适合交通工程师直接修改策略，适用于突发事件快速响应场景。
交通信号控制需兼顾有效性与可解释性，但强化学习产生黑箱策略，程序合成依赖受限领域语言。我们提出SignalClaw框架，利用大语言模型作为演化技能生成器，为自适应交通信号控制合成并优化可解释的控制策略。每个策略包含推理依据、选择指引与可执行代码，实现人类可检视与自文档化。每代演化中，仿真指标如队列百分位、延误趋势和停滞状态转化为自然语言反馈，指导改进。系统引入事件驱动的组合演化：事件检测器通过TraCI识别应急车辆、公交优先、事故与拥堵，优先调度器选择专用技能。各技能独立演化，通过优先级链实现在不重新训练的情况下运行时组合。在SUMO的常规与事件注入场景中评估，对比四种基线。常规场景下平均延迟7.8–9.2秒，仅比最优方法低3–10%，且随机种子间方差小。事件场景中，应急延迟11.2–18.5秒（MaxPressure为42.3–72.3，DQN为78.5–95.3），公交乘客延迟9.8–11.5秒（MaxPressure为38.7–45.2）。混合事件下调度器有效组合技能，整体延迟稳定。演化出的策略从简单线性规则逐步发展为多特征交互的条件策略，仍保持完全可解释且可由交通工程师直接修改。
原文摘要 · Abstract (English)
Traffic signal control TSC requires strategies that are both effective and interpretable for deployment, yet reinforcement learning produces opaque neural policies while program synthesis depends on restrictive domain-specific languages. We present SIGNALCLAW, a framework that uses large language models LLMs as evolutionary skill generators to synthesize and refine interpretable control skills for adaptive TSC. Each skill includes rationale, selection guidance, and executable code, making policies human-inspectable and self-documenting. At each generation, evolution signals from simulation metrics such as queue percentiles, delay trends, and stagnation are translated into natural language feedback to guide improvement. SignalClaw also introduces event-driven compositional evolution: an event detector identifies emergency vehicles, transit priority, incidents, and congestion via TraCI, and a priority dispatcher selects specialized skills. Each skill is evolved independently, and a priority chain enables runtime composition without retraining. We evaluate SignalClaw on routine and event-injected SUMO scenarios against four baselines. On routine scenarios, it achieves average delay of 7.8 to 9.2 seconds, within 3 to 10 percent of the best method, with low variance across random seeds. Under event scenarios, it yields the lowest emergency delay 11.2 to 18.5 seconds versus 42.3 to 72.3 for MaxPressure and 78.5 to 95.3 for DQN, and the lowest transit person delay 9.8 to 11.5 seconds versus 38.7 to 45.2 for MaxPressure. In mixed events, the dispatcher composes skills effectively while maintaining stable overall delay. The evolved skills progress from simple linear rules to conditional strategies with multi-feature interactions, while remaining fully interpretable and directly modifiable by traffic engineers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。