mlsanityData to 7 Oct 2026

VLA for autonomous driving

101 papers1 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: driving, autonomous driving, autonomous, reasoning, vla

Key facts. VLA for autonomous driving: 101 papers on arXiv since 2025 (data through 7 Oct 2026). 58 of its 101 mapped papers (57%) cite “AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning” (2025, arXiv 2506.13757). 43 of its 101 mapped papers (43%) cite “OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model” (2025, arXiv 2503.23463). 7 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

7 new papers, 17 Sep – 7 Oct; 1 this week.

  1. This week · 1
  2. Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving
  3. Earlier · 6
  4. Vision-Language-Action Autonomous Driving Agent with Language-based Memory
  5. CAR-VLA: Complexity-Aware and Risk-Adaptive Reasoning for Autonomous Driving
  6. RefineDrive: Reliable Failure-Guided Learning for Vision-Language-Action Driving
  7. CausalDriveBench: Evaluating Causal Reasoning in Vision-Language-Action Models for Autonomous Driving
  8. Less Language, More Latents: Annotation-Efficient VLAs for Driving
  9. PRIME: Perception Feedback with Situational Memory Embeddings in VLA Models

Foundations

Most cited by papers here

  1. AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning2025cited by 58 here
  2. OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model2025cited by 43 here
  3. DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving2025cited by 33 here
  4. Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail2025cited by 25 here
  5. DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving2025cited by 22 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 14 here
  2. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 26 here
  3. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 17 here
  4. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 6 here
  5. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 12 here
  6. 2025DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Drivingcited by 22 here
  7. 2025AutoDrive-R2: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Drivingcited by 8 here
  8. 2025MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learningcited by 7 here
16 more it builds on, not in this chain
  1. 2024Robotic Control via Embodied Chain-of-Thought Reasoningcited by 4 here
  2. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 6 here
  3. 2025OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Modelcited by 43 here
  4. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challengescited by 5 here
  5. 2025FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Drivingcited by 20 here
  6. 2025Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Modelscited by 17 here
  7. 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuningcited by 58 here
  8. 2025A Survey on Vision-Language-Action Models for Autonomous Drivingcited by 11 here
  9. 2025IRL-VLA: Training an Vision-Language-Action Policy via Reward World Modelcited by 6 here
  10. 2025Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Drivingcited by 7 here
  11. 2025DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Drivingcited by 33 here
  12. 2025Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tailcited by 25 here
  13. 2025Vision-Language-Action Models for Autonomous Driving: Past, Present, and Futurecited by 5 here
  14. 2026DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Drivingcited by 7 here
  15. 2026NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoningcited by 5 here
  16. 2026LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Drivingcited by 6 here

The 24 most cited of 155.

Browse

30 of 101, ranked 6–35

  1. 6FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving202520
  2. 7Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models202517
  3. 8A Survey on Vision-Language-Action Models for Autonomous Driving202511
  4. 9AutoDrive-R2: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving20258
  5. 10DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving20267
  6. 11Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving20257
  7. 12MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning20257
  8. 13LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving20266
  9. 14IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model20256
  10. 15NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning20265
All 30
  1. 16Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future20255
  2. 17DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Driving20264
  3. 18Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from Failures20264
  4. 19Unifying Language-Action Understanding and Generation for Autonomous Driving20264
  5. 20DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving20264
  6. 21OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervision20254
  7. 22WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving20254
  8. 23Latent Chain-of-Thought World Modeling for End-to-End Driving20254
  9. 24HiST-VLA: A Hierarchical Spatio-Temporal Vision-Language-Action Model for End-to-End Autonomous Driving20263
  10. 25UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving20263
  11. 26ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving20263
  12. 27DriveAction: A Benchmark for Exploring Human-like Driving Decisions in VLA Models20253
  13. 28FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning20253
  14. 29Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving20253
  15. 30DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning20253
  16. 31Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoning20253
  17. 32Generative Scenario Rollouts for End-to-End Autonomous Driving20262
  18. 33SteerVLA: Steering Vision-Language-Action Models in Long-Tail Driving Scenarios20262
  19. 34AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture-of-Transformers for End-to-End Autonomous Driving20262
  20. 35Efficient and Explainable End-to-End Autonomous Driving via Masked Vision-Language-Action Diffusion20261