# VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecture

arXiv: https://arxiv.org/abs/2505.19486 · HTML: https://mlsanity.com/paper/2505.19486/

## Key facts

- Cited by 3 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 25 of its 46 references that are in the map.
- First posted on arXiv 26 May 2025.

## Placed in

- LLM reasoning / [Chain-of-thought reasoning for driving](https://mlsanity.com/lr/chain-of-thought-reasoning-for-driving/)

## Builds on (most cited first, 25 of 25)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning](https://mlsanity.com/paper/2109.12674/) (2021)
- [Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control](https://mlsanity.com/paper/1903.04527/) (2019)
- [CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification](https://mlsanity.com/paper/1903.09254/) (2019)
- [A Survey on Traffic Signal Control Methods](https://mlsanity.com/paper/1904.08117/) (2019)
- [LLMLight: Large Language Models as Traffic Signal Control Agents](https://mlsanity.com/paper/2312.16044/) (2023)
- [AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Control](https://mlsanity.com/paper/2010.05772/) (2020)
- [Deep Reinforcement Learning for Traffic Light Control in Vehicular Networks](https://mlsanity.com/paper/1803.11115/) (2018)
- [LLM-Assisted Light: Leveraging Large Language Model Capabilities for Human-Mimetic Traffic Signal Control in Complex Urban Environments](https://mlsanity.com/paper/2403.08337/) (2024)
- [iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvement](https://mlsanity.com/paper/2407.06025/) (2024)
- [LibSignal: An Open Library for Traffic Signal Control](https://mlsanity.com/paper/2211.10649/) (2022)
- [SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Control](https://mlsanity.com/paper/2211.10871/) (2022)
- [Reinforcement Learning Approaches for Traffic Signal Control under Missing Data](https://mlsanity.com/paper/2304.10722/) (2023)
- [UniTSA: A Universal Reinforcement Learning Framework for V2X Traffic Signal Control](https://mlsanity.com/paper/2312.05090/) (2023)
- [A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehicles](https://mlsanity.com/paper/2111.00278/) (2021)
- [Traffic Signal Cycle Control with Centralized Critic and Decentralized Actors under Varying Intervention Frequencies](https://mlsanity.com/paper/2406.08248/) (2024)
- [MalLight: Influence-Aware Coordinated Traffic Signal Control for Traffic Signal Malfunctions](https://mlsanity.com/paper/2408.09768/) (2024)
- [SynTraC: A Synthetic Dataset for Traffic Signal Control from Traffic Monitoring Cameras](https://mlsanity.com/paper/2408.09588/) (2024)
- [DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data](https://mlsanity.com/paper/2410.22938/) (2024)

## Built on by (most cited first, 3 of 3)

- [Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems](https://mlsanity.com/paper/2508.02344/) (2025)
- [ReasonLight: A Multimodal Foundation Model-Enhanced Reinforcement Learning Framework for Zero-Shot Traffic Signal Control](https://mlsanity.com/paper/2605.29425/) (2026)
- [VLALight: A Vision-Language-Action Model for Traffic Signal Control](https://mlsanity.com/paper/2609.36934/) (2026)

## Abstract (arXiv)

Traffic signal control (TSC) is a core challenge in urban mobility, where real-time decisions must balance efficiency and safety. Existing methods - ranging from rule-based heuristics to reinforcement learning (RL) - often struggle to generalize to complex, dynamic, and safety-critical scenarios. We introduce VLMLight, a novel TSC framework that integrates vision-language meta-control with dual-branch reasoning. At the core of VLMLight is the first image-based traffic simulator that enables multi-view visual perception at intersections, allowing policies to reason over rich cues such as vehicle type, motion, and spatial density. A large language model (LLM) serves as a safety-prioritized meta-controller, selecting between a fast RL policy for routine traffic and a structured reasoning branch for critical cases. In the latter, multiple LLM agents collaborate to assess traffic phases, prioritize emergency vehicles, and verify rule compliance. Experiments show that VLMLight reduces waiting times for emergency vehicles by up to 65% over RL-only systems, while preserving real-time performance in standard conditions with less than 1% degradation. VLMLight offers a scalable, interpretable, and safety-aware solution for next-generation traffic signal control.