# VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving

arXiv: https://arxiv.org/abs/2412.15544 · HTML: https://mlsanity.com/paper/2412.15544/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- Placed in Driving VLMs and open-vocabulary detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 26 of its 55 references that are in the map.
- First posted on arXiv 20 Dec 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Driving VLMs and open-vocabulary detection](https://mlsanity.com/mllm/driving-vlms-and-open-vocabulary-detection/)
- End-to-end autonomous driving / [Reasoning VLA and VLM driving policies](https://mlsanity.com/driving/reasoning-vla-and-vlm-driving-policies/)

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [Language to Rewards for Robotic Skill Synthesis](https://mlsanity.com/paper/2306.08647/) (2023)
- [Reward Design with Language Models](https://mlsanity.com/paper/2303.00001/) (2023)
- [DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving](https://mlsanity.com/paper/2312.09245/) (2023)
- [DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models](https://mlsanity.com/paper/2309.16292/) (2023)
- [Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning](https://mlsanity.com/paper/2310.12921/) (2023)
- [RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback](https://mlsanity.com/paper/2402.03681/) (2024)
- [RoboCLIP: One Demonstration is Enough to Learn Robot Policies](https://mlsanity.com/paper/2310.07899/) (2023)
- [Vision-Language Models as a Source of Rewards](https://mlsanity.com/paper/2312.09187/) (2023)
- [V2X-VLM: End-to-End V2X Cooperative Autonomous Driving Through Large Vision-Language Models](https://mlsanity.com/paper/2408.09251/) (2024)
- [Language Reward Modulation for Pretraining Reinforcement Learning](https://mlsanity.com/paper/2308.12270/) (2023)
- [Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving](https://mlsanity.com/paper/2405.15324/) (2024)
- [Code as Reward: Empowering Reinforcement Learning with VLMs](https://mlsanity.com/paper/2402.04764/) (2024)
- [DriVLMe: Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experiences](https://mlsanity.com/paper/2406.03008/) (2024)
- [FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning](https://mlsanity.com/paper/2406.00645/) (2024)
- [REvolve: Reward Evolution with Large Language Models using Human Feedback](https://mlsanity.com/paper/2406.01309/) (2024)
- [A Review of Reward Functions for Reinforcement Learning in the context of Autonomous Driving](https://mlsanity.com/paper/2405.01440/) (2024)
- [Human-centric Reward Optimization for Reinforcement Learning-based Automated Driving using Large Language Models](https://mlsanity.com/paper/2405.04135/) (2024)
- [HighwayLLM: Decision-Making and Navigation in Highway Driving with RL-Informed Language Model](https://mlsanity.com/paper/2405.13547/) (2024)
- [Trustworthy Human-AI Collaboration: Reinforcement Learning with Human Feedback and Physics Knowledge for Safe Autonomous Driving](https://mlsanity.com/paper/2409.00858/) (2024)
- [LORD: Large Models based Opposite Reward Design for Autonomous Driving](https://mlsanity.com/paper/2403.18965/) (2024)

## Built on by (most cited first, 30 of 51)

- [A Survey on Vision-Language-Action Models for Autonomous Driving](https://mlsanity.com/paper/2506.24044/) (2025)
- [AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving](https://mlsanity.com/paper/2505.15298/) (2025)
- [Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models](https://mlsanity.com/paper/2505.16854/) (2025)
- [Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap](https://mlsanity.com/paper/2503.21411/) (2025)
- [MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning](https://mlsanity.com/paper/2512.13636/) (2025)
- [AutoNeural: Co-Designing Vision-Language Models for NPU Inference](https://mlsanity.com/paper/2512.02924/) (2025)
- [Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms](https://mlsanity.com/paper/2604.23775/) (2026)
- [CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Models](https://mlsanity.com/paper/2502.15119/) (2025)
- [Reflection-Based Task Adaptation for Self-Improving VLA](https://mlsanity.com/paper/2510.12710/) (2025)
- [Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happen](https://mlsanity.com/paper/2505.21743/) (2025)
- [HERMES: A Holistic End-to-End Risk-Aware Multimodal Embodied System with Vision-Language Models for Long-Tail Autonomous Driving](https://mlsanity.com/paper/2602.00993/) (2026)
- [HCRMP: A LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving](https://mlsanity.com/paper/2505.15793/) (2025)
- [VLAD: A VLM-Augmented Autonomous Driving Framework with Hierarchical Planning and Interpretable Decision Process](https://mlsanity.com/paper/2507.01284/) (2025)
- [Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience](https://mlsanity.com/paper/2505.05515/) (2025)
- [DriveMind: A Dual Visual Language Model-based Reinforcement Learning Framework for Autonomous Driving](https://mlsanity.com/paper/2506.00819/) (2025)
- [SEAL: Vision-Language Model-Based Safe End-to-End Cooperative Autonomous Driving with Adaptive Long-Tail Modeling](https://mlsanity.com/paper/2506.21041/) (2025)
- [Edge-Based Multimodal Sensor Data Fusion with Vision Language Models (VLMs) for Real-time Autonomous Vehicle Accident Avoidance](https://mlsanity.com/paper/2508.01057/) (2025)
- [Automated Reward Design for Gran Turismo](https://mlsanity.com/paper/2511.02094/) (2025)
- [Training and Benchmarking Code Generation for Physics-Inspired Animations](https://mlsanity.com/paper/2602.10840/) (2026)
- [SimpleVSF: VLM-Scoring Fusion for Trajectory Prediction of End-to-End Autonomous Driving](https://mlsanity.com/paper/2510.17191/) (2025)
- [SafeCoop: Unravelling Full Stack Safety in Agentic Collaborative Driving](https://mlsanity.com/paper/2510.18123/) (2025)
- [One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models](https://mlsanity.com/paper/2507.07709/) (2025)
- [COVLM-RL: Critical Object-Oriented Reasoning for Autonomous Driving Using VLM-Guided Reinforcement Learning](https://mlsanity.com/paper/2512.09349/) (2025)
- [Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous Driving](https://mlsanity.com/paper/2604.03497/) (2026)
- [SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning](https://mlsanity.com/paper/2604.24729/) (2026)
- [WCog-VLA: A Dual-Level World-Cognitive Vision-Language-Action Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2607.08375/) (2026)
- [Vision--Language Signals in Constrained RL: Safety Gains Without Anticipation](https://mlsanity.com/paper/2609.34041/) (2026)
- [ROAD: Responsibility-Oriented Reward Design for Reinforcement Learning in Autonomous Driving](https://mlsanity.com/paper/2505.24317/) (2025)
- [STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in Vision](https://mlsanity.com/paper/2508.08688/) (2025)
- [Orchestrate, Generate, Reflect: A VLM-Based Multi-Agent Collaboration Framework for Automated Driving Policy Learning](https://mlsanity.com/paper/2509.17042/) (2025)

## Abstract (arXiv)

In recent years, reinforcement learning (RL)-based methods for learning driving policies have gained increasing attention in the autonomous driving community and have achieved remarkable progress in various driving scenarios. However, traditional RL approaches rely on manually engineered rewards, which require extensive human effort and often lack generalizability. To address these limitations, we propose VLM-RL, a unified framework that integrates pre-trained Vision-Language Models (VLMs) with RL to generate reward signals using image observation and natural language goals. The core of VLM-RL is the contrasting language goal (CLG)-as-reward paradigm, which uses positive and negative language goals to generate semantic rewards. We further introduce a hierarchical reward synthesis approach that combines CLG-based semantic rewards with vehicle state information, improving reward stability and offering a more comprehensive reward signal. Additionally, a batch-processing technique is employed to optimize computational efficiency during training. Extensive experiments in the CARLA simulator demonstrate that VLM-RL outperforms state-of-the-art baselines, achieving a 10.5% reduction in collision rate, a 104.6% increase in route completion rate, and robust generalization to unseen driving scenarios. Furthermore, VLM-RL can seamlessly integrate almost any standard RL algorithms, potentially revolutionizing the existing RL paradigm that relies on manual reward engineering and enabling continuous performance improvements. The demo video and code can be accessed at: https://zilin-huang.github.io/VLM-RL-website.