{"ID":2886896,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.02344","arxiv_id":"2508.02344","title":"Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems","abstract":"We introduce Traffic-R1, a 3B-parameter foundation model with human-like reasoning for Traffic signal control (TSC), developed via self-exploration and iterative reinforcement of LLM with expert guidance in a simulated traffic environment. Compared with traditional reinforcement learning and recent LLM-based methods, Traffic-R1 offers three main advantages: zero-shot generalization, transferring unchanged to new road networks and out-of-distribution incidents by leveraging internal traffic-control policies and reasoning; a compact 3B-parameter design that supports real-time inference on mobile-class chips for edge deployment; and an explainable TSC process that enables multi-intersection coordination through communication and an asynchronous communication network. Extensive benchmarks show Traffic-R1 outperforms strong baselines and training-intensive RL controllers. In production, the model now manages signals affecting over 55,000 drivers daily, reduces average queue lengths by more than 5%, and halves operator workload. Our model is available at https://huggingface.co/Season998/Traffic-R1.","short_abstract":"We introduce Traffic-R1, a 3B-parameter foundation model with human-like reasoning for Traffic signal control (TSC), developed via self-exploration and iterative reinforcement of LLM with expert guidance in a simulated traffic environment. Compared with traditional reinforcement learning and recent LLM-based methods, T...","url_abs":"https://arxiv.org/abs/2508.02344","url_pdf":"https://arxiv.org/pdf/2508.02344v2","authors":"[\"Xingchen Zou\",\"Yuhao Yang\",\"Zheng Chen\",\"Xixuan Hao\",\"Yiqi Chen\",\"Chao Huang\",\"Yuxuan Liang\"]","published":"2025-08-04T12:25:19Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"LoRA\"]","has_code":false}