# AutoDrive-R2: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving

arXiv: https://arxiv.org/abs/2509.01944 · HTML: https://mlsanity.com/paper/2509.01944/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Placed in VLA for autonomous driving, one of 13 directions in Vision-language-action models.
- Builds on 34 of its 42 references that are in the map.
- First posted on arXiv 2 Sep 2025.

## Placed in

- Vision-language-action models / [VLA for autonomous driving](https://mlsanity.com/vla/vla-for-autonomous-driving/)
- 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, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023)
- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022)
- [DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model](https://mlsanity.com/paper/2310.01412/) (2023)
- [Scaling Relationship on Learning Mathematical Reasoning with Large Language Models](https://mlsanity.com/paper/2308.01825/) (2023)
- [LMDrive: Closed-Loop End-to-End Driving with Large Language Models](https://mlsanity.com/paper/2312.07488/) (2023)
- [VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning](https://mlsanity.com/paper/2402.13243/) (2024)
- [Learning to Drive in a Day](https://mlsanity.com/paper/1807.00412/) (2018)
- [AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.13757/) (2025)
- [Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?](https://mlsanity.com/paper/2312.03031/) (2023)
- [SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation](https://mlsanity.com/paper/2405.19620/) (2024)
- [DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving](https://mlsanity.com/paper/2312.09245/) (2023)
- [Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes](https://mlsanity.com/paper/2305.10430/) (2023)
- [OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model](https://mlsanity.com/paper/2503.23463/) (2025)
- [GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning](https://mlsanity.com/paper/2504.02546/) (2025)
- [MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices](https://mlsanity.com/paper/2312.16886/) (2023)
- [AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning](https://mlsanity.com/paper/2503.07608/) (2025)
- [DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving](https://mlsanity.com/paper/2505.16278/) (2025)
- [FusionAD: Multi-modality Fusion for Prediction and Planning Tasks of Autonomous Driving](https://mlsanity.com/paper/2308.01006/) (2023)
- [Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review](https://mlsanity.com/paper/2402.10086/) (2024)

## Built on by (most cited first, 30 of 34)

- [Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail](https://mlsanity.com/paper/2511.00088/) (2025)
- [Pure Vision Language Action (VLA) Models: A Comprehensive Survey](https://mlsanity.com/paper/2509.19012/) (2025)
- [MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning](https://mlsanity.com/paper/2512.13636/) (2025)
- [From Editor to Dense Geometry Estimator](https://mlsanity.com/paper/2509.04338/) (2025)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [PROGRESSLM: Towards Progress Reasoning in Vision-Language Models](https://mlsanity.com/paper/2601.15224/) (2026)
- [NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning](https://mlsanity.com/paper/2602.21172/) (2026)
- [Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving](https://mlsanity.com/paper/2511.19912/) (2025)
- [dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoning](https://mlsanity.com/paper/2512.04459/) (2025)
- [AutoDrive-P3: Unified Chain of Perception-Prediction-Planning Thought via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2603.28116/) (2026)
- [DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving](https://mlsanity.com/paper/2603.11041/) (2026)
- [Learning Vision-Language-Action World Models for Autonomous Driving](https://mlsanity.com/paper/2604.09059/) (2026)
- [MindDriver: Introducing Progressive Multimodal Reasoning for Autonomous Driving](https://mlsanity.com/paper/2602.21952/) (2026)
- [Unveiling the Cognitive Compass: Theory-of-Mind-Guided Multimodal Emotion Reasoning](https://mlsanity.com/paper/2602.00971/) (2026)
- [CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model](https://mlsanity.com/paper/2511.19914/) (2025)
- [One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies](https://mlsanity.com/paper/2603.12480/) (2026)
- [Accelerating Structured Chain-of-Thought in Autonomous Vehicles](https://mlsanity.com/paper/2602.02864/) (2026)
- [MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving](https://mlsanity.com/paper/2605.12624/) (2026)
- [Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI](https://mlsanity.com/paper/2510.04978/) (2025)
- [Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving](https://mlsanity.com/paper/2606.22913/) (2026)
- [OpenLongTail: Generative Scaling of Long-Tail Driving Data](https://mlsanity.com/paper/2607.09655/) (2026)
- [The Blind Spot of Adaptation: Quantifying and Mitigating Forgetting in Fine-tuned Driving Models](https://mlsanity.com/paper/2604.04857/) (2026)
- [Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling](https://mlsanity.com/paper/2605.13646/) (2026)
- [From Human Intention to Action Prediction: Intention-Driven End-to-End Autonomous Driving](https://mlsanity.com/paper/2512.12302/) (2025)
- [Latency Analysis and Optimization of Alpamayo 1 via Efficient Trajectory Generation](https://mlsanity.com/paper/2605.08975/) (2026)
- [PixelPilot: Scalable Vision-Language-Action Models for End-to-End Autonomous Driving](https://mlsanity.com/paper/2607.04637/) (2026)
- [MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models](https://mlsanity.com/paper/2607.09029/) (2026)
- [Drive the Thoughts: Runtime Monitoring of VLA Reasoning-Trajectory Consistency](https://mlsanity.com/paper/2608.29583/) (2026)
- [CoLT-Drive: Counterfactual Long-Tail Benchmarking and Knowledge-Preserving Adaptation for Driving Affordance Prediction](https://mlsanity.com/paper/2609.00242/) (2026)
- [Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving](https://mlsanity.com/paper/2609.01659/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models in autonomous driving systems have recently demonstrated transformative potential by integrating multimodal perception with decision-making capabilities. However, the interpretability and coherence of the decision process and the plausibility of action sequences remain largely underexplored. To address these issues, we propose AutoDrive-R2, a novel VLA framework that enhances both reasoning and self-reflection capabilities of autonomous driving systems through chain-of-thought (CoT) processing and reinforcement learning (RL). Specifically, we first propose an innovative CoT dataset named nuScenesR2-6K for supervised fine-tuning, which effectively builds cognitive bridges between input information and output trajectories through a four-step logical chain with self-reflection for validation. Moreover, to maximize both reasoning and self-reflection during the RL stage, we further employ the Group Relative Policy Optimization (GRPO) algorithm within a physics-grounded reward framework that incorporates spatial alignment, vehicle dynamic, and temporal smoothness criteria to ensure reliable and realistic trajectory planning. Extensive evaluation results across both nuScenes and Waymo datasets demonstrates the state-of-the-art performance and robust generalization capacity of our proposed method.