EvolveSignal: A Large Language Model Powered Coding Agent for Discovering Traffic Signal Control Algorithms
This work addresses the labor-intensive and suboptimal nature of fixed-time traffic signal control for traffic engineers, offering a novel AI-driven approach to algorithm design in transportation engineering.
The paper tackles the problem of designing traffic signal control algorithms by introducing EvolveSignal, an LLM-powered coding agent that automatically discovers new algorithms through program synthesis and evolutionary search, resulting in a 20.1% reduction in average delay and 47.1% reduction in average stops compared to baseline methods.
In traffic engineering, the fixed-time traffic signal control remains widely used for its low cost, stability, and interpretability. However, its design depends on hand-crafted formulas (e.g., Webster) and manual re-timing by engineers to adapt to demand changes, which is labor-intensive and often yields suboptimal results under heterogeneous or congested conditions. This paper introduces the EvolveSignal, a large language models (LLMs) powered coding agent to automatically discover new traffic signal control algorithms. We formulate the problem as program synthesis, where candidate algorithms are represented as Python functions with fixed input-output structures, and iteratively optimized through external evaluations (e.g., a traffic simulator) and evolutionary search. Experiments on a signalized intersection demonstrate that the discovered algorithms outperform Webster's baseline, reducing average delay by 20.1% and average stops by 47.1%. Beyond performance, ablation and incremental analyses reveal that EvolveSignal modifications-such as adjusting cycle length bounds, incorporating right-turn demand, and rescaling green allocations-can offer practically meaningful insights for traffic engineers. This work opens a new research direction by leveraging AI for algorithm design in traffic signal control, bridging program synthesis with transportation engineering.