mlsanityData to 7 Oct 2026

Reasoning VLA and VLM driving policies

232 papers3 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, reasoning, autonomous driving, autonomous, vla

Key facts. Reasoning VLA and VLM driving policies: 232 papers on arXiv since 2023 (data through 7 Oct 2026). 85 of its 232 mapped papers (37%) cite “AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning” (2025, arXiv 2506.13757). 71 of its 232 mapped papers (31%) cite “EMMA: End-to-End Multimodal Model for Autonomous Driving” (2024, arXiv 2410.23262). 13 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

13 new papers, 17 Sep – 7 Oct; 3 this week.

  1. This week · 3
  2. Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving
  3. Not All Uncertainty Matters: Simulation-in-the-Loop Fast-Slow Reasoning for Decision-Critical Autonomous Driving System
  4. Grounding What Shapes the Plan: Rethinking Groundedness for Physical Intelligence in Autonomous Driving also fits: Imitation-learning end-to-end planners
  5. Earlier · 10
  6. Vision-Language-Action Autonomous Driving Agent with Language-based Memory
  7. Data-Efficient Adaptation of a Driving VLA to Class 8 Trucks
  8. doPlan: A Variable-Horizon Dataset for Multi-Stage Language-Conditioned Planning in Autonomous Driving also fits: Large language models for driving
  9. Speed in the Blind Spot: An Interpretability Analysis of Dynamic Perception in VLMs for Autonomous Driving also fits: VLMs for autonomous driving
  10. CAR-VLA: Complexity-Aware and Risk-Adaptive Reasoning for Autonomous Driving
  11. RefineDrive: Reliable Failure-Guided Learning for Vision-Language-Action Driving
  12. CausalDriveBench: Evaluating Causal Reasoning in Vision-Language-Action Models for Autonomous Driving
All 13
  1. DriveHierarchy: A Benchmark for Diagnosing VLM Driving Capabilities from Open-Loop Understanding to Closed-Loop Execution also fits: VLMs for autonomous driving
  2. AnchorReasoning: A Visual Grounding and Causal Reasoning Dataset in Long-Tail Autonomous Driving Scenarios also fits: VLMs for autonomous driving
  3. Less Language, More Latents: Annotation-Efficient VLAs for Driving

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 85 here
  2. EMMA: End-to-End Multimodal Model for Autonomous Driving2024cited by 71 here
  3. ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation2025cited by 67 here
  4. OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model2025cited by 63 here
  5. Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving2024cited by 57 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2022ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learningcited by 65 here
  2. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 117 here
  3. 2023Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenescited by 46 here
  4. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 52 here
  5. 2023DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Modelcited by 95 here
  6. 2023LMDrive: Closed-Loop End-to-End Driving with Large Language Modelscited by 82 here
  7. 2023DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Drivingcited by 53 here
  8. 2023DriveLM: Driving with Graph Visual Question Answeringcited by 112 here
  9. 2024VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planningcited by 55 here
  10. 2024NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarkingcited by 59 here
  11. 2024EMMA: End-to-End Multimodal Model for Autonomous Drivingcited by 71 here
  12. 2025ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generationcited by 67 here
  13. 2025OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Modelcited by 63 here
11 more it builds on, not in this chain
  1. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 69 here
  2. 2022Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baselinecited by 47 here
  3. 2023Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?cited by 53 here
  4. 2024DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Modelscited by 124 here
  5. 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representationcited by 46 here
  6. 2024Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Drivingcited by 54 here
  7. 2024Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Drivingcited by 57 here
  8. 2024DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Drivingcited by 62 here
  9. 2025SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignmentcited by 53 here
  10. 2025ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Drivingcited by 50 here
  11. 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuningcited by 85 here

The 24 most cited of 577.

Browse

30 of 232, ranked 6–35

  1. 6SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment202553
  2. 7ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving202550
  3. 8AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning202545
  4. 9OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning202541
  5. 10Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail202541
  6. 11DriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Driving202431
  7. 12VLP: Vision Language Planning for Autonomous Driving202428
  8. 13DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving202524
  9. 14Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models202524
  10. 15A Survey on Vision-Language-Action Models for Autonomous Driving202522
All 30
  1. 16AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving202520
  2. 17DiffVLA: Vision-Language Guided Diffusion Planning for Autonomous Driving202518
  3. 18Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning202518
  4. 19OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning202418
  5. 20Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving202416
  6. 21Distilling Multi-modal Large Language Models for Autonomous Driving202515
  7. 22CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving202414
  8. 23WiseAD: Knowledge Augmented End-to-End Autonomous Driving with Vision-Language Model202413
  9. 24AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving202512
  10. 25SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving202512
  11. 26AutoDrive-R2: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving202512
  12. 27ADAPT: Action-aware Driving Caption Transformer202310
  13. 28Towards Knowledge-driven Autonomous Driving202310
  14. 29LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving20268
  15. 30Hint-AD: Holistically Aligned Interpretability in End-to-End Autonomous Driving20248
  16. 31FASIONAD : FAst and Slow FusION Thinking Systems for Human-Like Autonomous Driving with Adaptive Feedback20248
  17. 32VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving20248
  18. 33S4-Driver: Scalable Self-Supervised Driving Multimodal Large Language Modelwith Spatio-Temporal Visual Representation20257
  19. 34HMVLM: Multistage Reasoning-Enhanced Vision-Language Model for Long-Tailed Driving Scenarios20257
  20. 35DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking20257