mlsanityData to 14 Oct 2026

AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning

arXiv 2506.13757 ↗First posted 16 Jun 2025cs.CVcited by 260

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

also in 2 more
Abstract (arXiv)

Recent advancements in Vision-Language-Action (VLA) models have shown promise for end-to-end autonomous driving by leveraging world knowledge and reasoning capabilities. However, current VLA models often struggle with physically infeasible action outputs, complex model structures, or unnecessarily long reasoning. In this paper, we propose AutoVLA, a novel VLA model that unifies reasoning and action generation within a single autoregressive generation model for end-to-end autonomous driving. AutoVLA performs semantic reasoning and trajectory planning directly from raw visual inputs and language instructions. We tokenize continuous trajectories into discrete, feasible actions, enabling direct integration into the language model. For training, we employ supervised fine-tuning to equip the model with dual thinking modes: fast thinking (trajectory-only) and slow thinking (enhanced with chain-of-thought reasoning). To further enhance planning performance and efficiency, we introduce a reinforcement fine-tuning method based on Group Relative Policy Optimization (GRPO), reducing unnecessary reasoning in straightforward scenarios. Extensive experiments across real-world and simulated datasets and benchmarks, including nuPlan, nuScenes, Waymo, and CARLA, demonstrate the competitive performance of AutoVLA in both open-loop and closed-loop settings. Qualitative results showcase the adaptive reasoning and accurate planning capabilities of AutoVLA in diverse scenarios.

Key facts. Cited by 260 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 89 of its 105 references that are in the map. First posted on arXiv 16 Jun 2025.

Builds on

89 of 105 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025DSDrive: Distilling Large Language Model for Lightweight End-to-End Autonomous Driving with Unified Reasoning and Planning8 May
  2. 2025NuScenes-SpatialQA: A Spatial Understanding and Reasoning Benchmark for Vision-Language Models in Autonomous Driving4 Apr
  3. 2025ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation25 Mar
  4. 2025AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning10 Mar
  5. 2025CoT-Drive: Efficient Motion Forecasting for Autonomous Driving with LLMs and Chain-of-Thought Prompting10 Mar
  6. 2024VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision19 Dec
  7. 2024WiseAD: Knowledge Augmented End-to-End Autonomous Driving with Vision-Language Model13 Dec
  8. 2024WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving5 Jul
  9. 2024DriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Driving25 Mar
  10. 2023Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving6 Dec
  11. 2023Drive Like a Human: Rethinking Autonomous Driving with Large Language Models14 Jul

Other references · 78

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2025Qwen2.5-VL Technical Reportcited by 5,587
  6. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  7. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  8. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  9. 2022Planning-oriented Autonomous Drivingcited by 1,087
  10. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  11. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  12. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 622
38 more
  1. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 537
  2. 2023DriveLM: Driving with Graph Visual Question Answeringcited by 536
  3. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 490
  4. 2024DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Modelscited by 490
  5. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 485
  6. 2023DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Modelcited by 461
  7. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 451
  8. 2022ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learningcited by 368
  9. 2024NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarkingcited by 354
  10. 2023GPT-Driver: Learning to Drive with GPTcited by 347
  11. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 336
  12. 2024DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Drivingcited by 334
  13. 2023Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Drivingcited by 319
  14. 2023LMDrive: Closed-Loop End-to-End Driving with Large Language Modelscited by 305
  15. 2023NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenariocited by 262
  16. 2024Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Drivingcited by 252
  17. 2024Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillationcited by 249
  18. 2022Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baselinecited by 248
  19. 2023Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?cited by 242
  20. 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representationcited by 241
  21. 2023DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Drivingcited by 233
  22. 2024EMMA: End-to-End Multimodal Model for Autonomous Drivingcited by 231
  23. 2024GenAD: Generative End-to-End Autonomous Drivingcited by 225
  24. 2023Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenescited by 191
  25. 2025Reasoning Models Can Be Effective Without Thinkingcited by 187
  26. 2025OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Modelcited by 176
  27. 2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Drivingcited by 169
  28. 2024Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Drivingcited by 156
  29. 2025SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignmentcited by 150
  30. 2023LingoQA: Visual Question Answering for Autonomous Drivingcited by 145
  31. 2023DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Drivingcited by 144
  32. 2023GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Drivingcited by 141
  33. 2023MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Queryingcited by 140
  34. 2025NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Taskscited by 127
  35. 2023Vision Language Models in Autonomous Driving: A Survey and Outlookcited by 126
  36. 2024VLP: Vision Language Planning for Autonomous Drivingcited by 126
  37. 2023Dolphins: Multimodal Language Model for Drivingcited by 124
  38. 2023Language Prompt for Autonomous Drivingcited by 111

50 most cited of 78 All 78 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 52; 2026: 208.

260 papers.

Sort:

By area:

  1. 2025Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tailcited by 146
  2. 2025DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Drivingcited by 134
  3. 2025A Survey on Vision-Language-Action Models for Autonomous Drivingcited by 72
  4. 2025WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarioscited by 62
  5. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 49
  6. 2026Driving on Registerscited by 44
  7. 2025RAP: 3D Rasterization Augmented End-to-End Planningcited by 41
  8. 2026SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Drivingcited by 38
  9. 2026DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Drivingcited by 37
  10. 2025AutoDrive-R2: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Drivingcited by 34
  11. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  12. 2025OmniNWM: Omniscient Driving Navigation World Modelscited by 33
38 more
  1. 2025Vision-Language-Action Models for Autonomous Driving: Past, Present, and Futurecited by 33
  2. 2025SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Drivingcited by 28
  3. 2026LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Drivingcited by 28
  4. 2025ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Drivingcited by 25
  5. 2025MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learningcited by 25
  6. 2025Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Drivingcited by 24
  7. 2026DriveVA: Video Action Models are Zero-Shot Driverscited by 23
  8. 2025Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoningcited by 22
  9. 2025DVGT: Driving Visual Geometry Transformercited by 21
  10. 2026VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Drivingcited by 20
  11. 2026DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Drivingcited by 19
  12. 2026Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from Failurescited by 19
  13. 2026UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Drivingcited by 19
  14. 2026Fail2Drive: Benchmarking Closed-Loop Driving Generalizationcited by 17
  15. 2026SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Modelcited by 17
  16. 2026DriveFuture: Future-Aware Latent World Models for Autonomous Drivingcited by 17
  17. 2025Zero-Human Demonstration End-to-end Autonomous Driving with Trajectory Scorercited by 16
  18. 2025WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Drivingcited by 16
  19. 2025Latent Chain-of-Thought World Modeling for End-to-End Drivingcited by 15
  20. 2026Devil is in Narrow Policy: Unleashing Exploration in Driving VLA Modelscited by 15
  21. 2026DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Drivingcited by 15
  22. 2026EponaV2: Driving World Model with Comprehensive Future Reasoningcited by 15
  23. 2025dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoningcited by 14
  24. 2026AutoDrive-P3: Unified Chain of Perception-Prediction-Planning Thought via Reinforcement Fine-Tuningcited by 14
  25. 2026DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Drivingcited by 14
  26. 2026DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scalecited by 13
  27. 2025MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Drivingcited by 12
  28. 2026ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Drivingcited by 12
  29. 2026CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Drivingcited by 12
  30. 2025OpenREAD: Reinforced Open-Ended Reasoning for End-to-End Autonomous Driving with LLM-as-Criticcited by 11
  31. 2026SteerVLA: Steering Vision-Language-Action Models in Long-Tail Driving Scenarioscited by 11
  32. 2026DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Drivingcited by 11
  33. 2026Uni-World VLA: Interleaved World Modeling and Planning for Autonomous Drivingcited by 11
  34. 2026Learning Vision-Language-Action World Models for Autonomous Drivingcited by 11
  35. 2026CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planningcited by 11
  36. 2026Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigationcited by 11
  37. 2026Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation Systemcited by 11
  38. 2025UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Drivingcited by 10

50 most cited of 260 All 260 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving
  2. 2025Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning
  3. 2025ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
  4. 2025DriveMind: A Dual Visual Language Model-based Reinforcement Learning Framework for Autonomous Driving
  5. 2025ColaVLA: Leveraging Cognitive Latent Reasoning for Hierarchical Parallel Trajectory Planning in Autonomous Driving
  6. 2025DriveRX: A Vision-Language Reasoning Model for Cross-Task Autonomous Driving
  7. 2025CoT4AD: A Vision-Language-Action Model with Explicit Chain-of-Thought Reasoning for Autonomous Driving
  8. 2026Judge, Then Drive: A Critic-Centric Vision Language Action Framework for Autonomous Driving