Metraipolis › archive › dc_cec3189995ef
EvoSignal: LLM-Guided Evolutionary Design of Modular Traffic Signal Control Programs — arXiv:2610.09563
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09563
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T11:56:46.317Z
- SHA-256 of the archived text
6fe2f32c8de13c40b196ad41cc8888e04938c2d141210f65da4927919fe87b22- Stable URL of this page
https://metraipolis.com/documento/dc_cec3189995ef
How to cite
EvoSignal: LLM-Guided Evolutionary Design of Modular Traffic Signal Control Programs — arXiv:2610.09563 — arXiv (en), https://arxiv.org/abs/2610.09563 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cec3189995ef (Metraipolis archive dc_cec3189995ef, sha256 6fe2f32c8de13c40b196ad41cc8888e04938c2d141210f65da4927919fe87b22)
BibTeX
@misc{dccec3189995ef,
title = {EvoSignal: LLM-Guided Evolutionary Design of Modular Traffic Signal Control Programs — arXiv:2610.09563},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09563},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cec3189995ef; sha256 6fe2f32c8de13c40b196ad41cc8888e04938c2d141210f65da4927919fe87b22},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09563. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Effective traffic signal control (TSC) requires policies that respond to changing traffic demand and network conditions while meeting different control objectives. However, adapting existing strategies often involves repeated manual design and adjustment, making it difficult to systematically explore better control rules for a target network. Large language models (LLMs) can automate this process, but directly using them to select signal phases leaves decision rules embedded in black-box models and incurs recurring inference costs and latency. This paper formulates TSC as a modular program design problem and proposes EvoSignal, an LLM-guided evolutionary framework using traffic knowledge and performance feedback. The modular representation separates traffic feature extraction, local phase prioritization, and optional network-based priority adjustment. Starting from several established strategies, EvoSignal improves programs through feedback on congestion and signal operation, retaining strategies with different performance trade-offs. The resulting programs operate without online LLM inference. Simulation experiments across five scenarios on two real-world road networks show that the selected default EvoSignal program reduces waiting time by 16.8--49.2\% relative to the lowest waiting time achieved by the 20 conventional, reinforcement learning-based, and LLM-based baselines in each scenario. A program prioritizing travel time and queue length outperforms all 20 baselines on all three metrics in the search scenario and remains among the top three on each metric when transferred unchanged to the other four scenarios. These findings support automated design of inspectable control programs that transfer across the evaluated road networks and traffic this http URL is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.09563 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T10:50:37.695Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).