mlsanityData to 14 Oct 2026

Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems

arXiv 2508.02344 ↗First posted 4 Aug 2025cs.AIcited by 12

On the map: LLM reasoning → Chain-of-thought reasoning for driving

Abstract (arXiv)

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.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Placed in Chain-of-thought reasoning for driving, one of 17 directions in LLM reasoning. Builds on 19 of its 58 references that are in the map. First posted on arXiv 4 Aug 2025.

Builds on

19 of 58 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecture26 May

Other references · 18

  1. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  2. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  3. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  4. 2024DeepSeek-V3 Technical Reportcited by 811
  5. 2024Large Language Models: A Surveycited by 525
  6. 2025RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learningcited by 386
  7. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 293
  8. 2022Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimizationcited by 246
  9. 2023DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Modelscited by 207
  10. 2023Vision Language Models in Autonomous Driving: A Survey and Outlookcited by 126
  11. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 111
  12. 2024Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Modelscited by 105
6 more
  1. 2023LLMLight: Large Language Models as Traffic Signal Control Agentscited by 73
  2. 2024LLM-Assisted Light: Leveraging Large Language Model Capabilities for Human-Mimetic Traffic Signal Control in Complex Urban Environmentscited by 31
  3. 2021Efficient Pressure: Improving efficiency for signalized intersectionscited by 24
  4. 2025CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Controlcited by 15
  5. 2022The Real Deal: A Review of Challenges and Opportunities in Moving Reinforcement Learning-Based Traffic Signal Control Systems Towards Realitycited by 9
  6. 2024TSCLIP: Robust CLIP Fine-Tuning for Worldwide Cross-Regional Traffic Sign Recognitioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 10.

12 papers.

  1. 2026TimeOmni-VL: Unified Models for Time Series Understanding and Generationcited by 7
  2. 2025Urban-R1: Reinforced MLLMs Mitigate Geospatial Biases for Urban General Intelligencecited by 3
  3. 2026ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuningcited by 3
  4. 2025A Dual Large Language Models Architecture with Herald Guided Prompts for Parallel Fine Grained Traffic Signal Controlcited by 2
  5. 2026SignalClaw: LLM-Guided Evolutionary Synthesis of Interpretable Traffic Signal Control Skillscited by 1
  6. 2026LLM Agents for Time-Series: A Surveycited by 1
  7. 2026CuraLight: Debate-Guided Data Curation for LLM-Centered Traffic Signal Controlcited by 0
  8. 2026DGLight: DQN-Guided GRPO Fine-Tuning of Large Language Models for Traffic Signal Controlcited by 0
  9. 2026ReasonLight: A Multimodal Foundation Model-Enhanced Reinforcement Learning Framework for Zero-Shot Traffic Signal Controlcited by 0
  10. 2026LLM-Based Hierarchical Coordinated Control with Continuation-Aware Policy Learningcited by 0
  11. 2026ProcessLight: Process Supervision for Large Language Model Based Traffic Signal Controlcited by 0
  12. 2026VLALight: A Vision-Language-Action Model for Traffic Signal Controlcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning
  2. 2026LATS: Large Language Model Assisted Teacher-Student Framework for Multi-Agent Reinforcement Learning in Traffic Signal Control
  3. 2025Robustness of Reinforcement Learning-Based Traffic Signal Control under Incidents: A Comparative Study
  4. 2026EvoSignal: LLM-Guided Evolutionary Design of Modular Traffic Signal Control Programs
  5. 2025Evolutionary Discovery of Heuristic Policies for Traffic Signal Control
  6. 2026Explainable Reinforcement Learning for Adaptive Traffic Signal Control
  7. 2023Traffic Signal Control Using Lightweight Transformers: An Offline-to-Online RL Approach
  8. 2024iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvement