mlsanityData to 7 Oct 2026

LLMLight: Large Language Models as Traffic Signal Control Agents

arXiv 2312.16044 ↗First posted 26 Dec 2023cs.AIcited by 73

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

Traffic Signal Control (TSC) is a crucial component in urban traffic management, aiming to optimize road network efficiency and reduce congestion. Traditional TSC methods, primarily based on transportation engineering and reinforcement learning (RL), often struggle with generalization abilities across varied traffic scenarios and lack interpretability. This paper presents LLMLight, a novel framework employing Large Language Models (LLMs) as decision-making agents for TSC. Specifically, the framework begins by instructing the LLM with a knowledgeable prompt detailing real-time traffic conditions. Leveraging the advanced generalization capabilities of LLMs, LLMLight engages a reasoning and decision-making process akin to human intuition for effective traffic control. Moreover, we build LightGPT, a specialized backbone LLM tailored for TSC tasks. By learning nuanced traffic patterns and control strategies, LightGPT enhances the LLMLight framework cost-effectively. Extensive experiments conducted on ten real-world and synthetic datasets, along with evaluations by fifteen human experts, demonstrate the exceptional effectiveness, generalization ability, and interpretability of LLMLight with LightGPT, outperforming nine baseline methods and ten advanced LLMs.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 20 of its 61 references that are in the map. First posted on arXiv 26 Dec 2023.

Builds on

20 of 61 references.

References · 20

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2020Scaling Laws for Neural Language Modelscited by 6,411
  4. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  5. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  6. 2023RRHF: Rank Responses to Align Language Models with Human Feedback without tearscited by 454
  7. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMscited by 319
  8. 2023FireAct: Toward Language Agent Fine-tuningcited by 247
  9. 2023LanguageMPC: Large Language Models as Decision Makers for Autonomous Drivingcited by 188
  10. 2019CoLight: Learning Network-level Cooperation for Traffic Signal Controlcited by 133
  11. 2023Drive as You Speak: Enabling Human-Like Interaction with Large Language Models in Autonomous Vehiclescited by 100
  12. 2019A Survey on Traffic Signal Control Methodscited by 78
8 more
  1. 2023Penetrative AI: Making LLMs Comprehend the Physical Worldcited by 64
  2. 2020AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Controlcited by 60
  3. 2022Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Modelscited by 28
  4. 2021Efficient Pressure: Improving efficiency for signalized intersectionscited by 24
  5. 2023UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Predictioncited by 20
  6. 2023Irregular Traffic Time Series Forecasting Based on Asynchronous Spatio-Temporal Graph Convolutional Networkcited by 19
  7. 2023Robust Spatiotemporal Traffic Forecasting with Reinforced Dynamic Adversarial Trainingcited by 9
  8. 2023A Preference-aware Meta-optimization Framework for Personalized Vehicle Energy Consumption Estimationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 29; 2026: 39.

73 papers.

Sort:

By area:

  1. 2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Surveycited by 93
  2. 2024AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Predictioncited by 25
  3. 2024Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Modelscited by 23
  4. 2025Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directionscited by 23
  5. 2025Foundation Models for Spatio-Temporal Data Science: A Tutorial and Surveycited by 23
  6. 2025Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systemscited by 12
  7. 2025ARROW: An Adaptive Rollout and Routing Method for Global Weather Forecastingcited by 8
  8. 2025CrashSage: A Large Language Model-Centered Framework for Contextual and Interpretable Traffic Crash Analysiscited by 6
  9. 2024TraveLLM: Could you plan my new public transit route in face of a network disruption?cited by 5
  10. 2025USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning of LLMs as Urban Agentscited by 5
  11. 2025Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectivescited by 4
  12. 2025Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applicationscited by 4
38 more
  1. 2024Beyond Words: Evaluating Large Language Models in Transportation Planningcited by 3
  2. 2025VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecturecited by 3
  3. 2025SUMO-MCP: Leveraging the Model Context Protocol for Autonomous Traffic Simulation and Optimizationcited by 3
  4. 2025Urban-R1: Reinforced MLLMs Mitigate Geospatial Biases for Urban General Intelligencecited by 3
  5. 2025Aligning LLM agents with human learning and adjustment behavior: a dual agent approachcited by 3
  6. 2025AgentSUMO: An Agentic Framework for Interactive Simulation Scenario Generation in SUMO via Large Language Modelscited by 3
  7. 2025TrafficSimAgent: A Hierarchical Agent Framework for Autonomous Traffic Simulation with MCP Controlcited by 3
  8. 2025Urban Computing in the Era of Large Language Modelscited by 2
  9. 2025LLM-ODDR: A Large Language Model Framework for Joint Order Dispatching and Driver Repositioningcited by 2
  10. 2025SymLight: Exploring Interpretable and Deployable Symbolic Policies for Traffic Signal Controlcited by 2
  11. 2026OPTIAGENT: A Physics-Driven Agentic Framework for Automated Optical Designcited by 2
  12. 2025Chat2SPaT: A Large Language Model Based Tool for Automating Traffic Signal Control Plan Managementcited by 1
  13. 2025EvolveSignal: A Large Language Model Powered Coding Agent for Discovering Traffic Signal Control Strategiescited by 1
  14. 2025An LLM-Powered Cooperative Framework for Large-Scale Multi-Vehicle Navigationcited by 1
  15. 2025SVBRD-LLM: Self-Verifying Behavioral Rule Discovery for Autonomous Vehicle Identificationcited by 1
  16. 2025Evolutionary Discovery of Heuristic Policies for Traffic Signal Controlcited by 1
  17. 2026Virtual Traffic Police: Large Language Model-Augmented Traffic Signal Control for Unforeseen Incidentscited by 1
  18. 2026Human-Centric Traffic Signal Control for Equity: A Multi-Agent Action Branching Deep Reinforcement Learning Approachcited by 1
  19. 2026SignalClaw: LLM-Guided Evolutionary Synthesis of Interpretable Traffic Signal Control Skillscited by 1
  20. 2026ARMove: Learning to Predict Human Mobility through Agentic Reasoningcited by 1
  21. 2026Task-Aware Harness Provisioning for LLM Agents in Mission-Critical Infrastructure Operationscited by 1
  22. 2026LLM Agents for Time-Series: A Surveycited by 1
  23. 2024Bayesian Critique-Tune-Based Reinforcement Learning with Adaptive Pressure for Multi-Intersection Traffic Signal Controlcited by 0
  24. 2025Visual Reasoning at Urban Intersections: FineTuning GPT-4o for Traffic Conflict Detectioncited by 0
  25. 2025GraphTrafficGPT: Enhancing Traffic Management Through Graph-Based AI Agent Coordinationcited by 0
  26. 2025LinguaFluid: Language Guided Fluid Control via Semantic Rewards in Reinforcement Learningcited by 0
  27. 2025TransLLM: A Unified Multi-Task Foundation Framework for Urban Transportation via Learnable Promptingcited by 0
  28. 2025Retrieval Augmented Generation-Enhanced Distributed LLM Agents for Generalizable Traffic Signal Control with Emergency Vehiclescited by 0
  29. 2025Can a Small Model Learn to Look Before It Leaps? Dynamic Learning and Proactive Correction for Hallucination Detectioncited by 0
  30. 2026Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Makingcited by 0
  31. 2026HiVid: LLM-Guided Video Saliency For Content-Aware VOD And Live Streamingcited by 0
  32. 2026Spatio-temporal dual-stage hypergraph MARL for human-centric multimodal corridor traffic signal controlcited by 0
  33. 2026Emergency Preemption Without Online Exploration: A Decision Transformer Approachcited by 0
  34. 2026CuraLight: Debate-Guided Data Curation for LLM-Centered Traffic Signal Controlcited by 0
  35. 2026C2T: Captioning-Structure and LLM-Aligned Common-Sense Reward Learning for Traffic--Vehicle Coordinationcited by 0
  36. 2026TrafficClaw: A Generalizable LLM Agent in the Unified Physical Environment for Urban Traffic Controlcited by 0
  37. 2026GeoMind: An Agentic Workflow for Lithology Classification with Reasoned Tool Invocationcited by 0
  38. 2026LLM-Augmented Traffic Signal Control with LSTM-Based Traffic State Prediction and Safety-Constrained Decision Supportcited by 0

50 most cited of 73 All 73 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025A Dual Large Language Models Architecture with Herald Guided Prompts for Parallel Fine Grained Traffic Signal Control
  2. 2025CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control
  3. 2026LATS: Large Language Model Assisted Teacher-Student Framework for Multi-Agent Reinforcement Learning in Traffic Signal Control
  4. 2024Large Language Models (LLMs) as Traffic Control Systems at Urban Intersections: A New Paradigm
  5. 2025LLM-Guided Reinforcement Learning with Representative Agents for Traffic Modeling
  6. 2023Traffic Signal Control Using Lightweight Transformers: An Offline-to-Online RL Approach
  7. 2025Large Language Models and Their Applications in Roadway Safety and Mobility Enhancement: A Comprehensive Review
  8. 2025LLM-ABM for Transportation: Assessing the Potential of LLM Agents in System Analysis