# SignalClaw: LLM-Guided Evolutionary Synthesis of Interpretable Traffic Signal Control Skills

arXiv: https://arxiv.org/abs/2604.05535 · HTML: https://mlsanity.com/paper/2604.05535/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 9 of 9)

- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Verifiable Reinforcement Learning via Policy Extraction](https://mlsanity.com/paper/1805.08328/) (2018)
- [CoLight: Learning Network-level Cooperation for Traffic Signal Control](https://mlsanity.com/paper/1905.05717/) (2019)
- [Learning Phase Competition for Traffic Signal Control](https://mlsanity.com/paper/1905.04722/) (2019)
- [LLMLight: Large Language Models as Traffic Signal Control Agents](https://mlsanity.com/paper/2312.16044/) (2023)
- [Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI](https://mlsanity.com/paper/2507.14172/) (2025)
- [Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems](https://mlsanity.com/paper/2508.02344/) (2025)
- [SymLight: Exploring Interpretable and Deployable Symbolic Policies for Traffic Signal Control](https://mlsanity.com/paper/2511.05790/) (2025)
- [Evolutionary Discovery of Heuristic Policies for Traffic Signal Control](https://mlsanity.com/paper/2511.23122/) (2025)

## Built on by (most cited first, 1 of 1)

- [EvoSignal: LLM-Guided Evolutionary Design of Modular Traffic Signal Control Programs](https://mlsanity.com/paper/2610.09563/) (2026)

## Abstract (arXiv)

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.