Reflect-VLA: Internalizing Reflective Guidance via Dual-Path On-Policy Self-Distillation for Autonomous Driving

arXiv:2610.13453 · cs.RO · Submitted 2026-10-09 · Read on arXiv

cs.RO

Submitted: 2026-10-09

Updated: 2026-10-09

Code: https://github.com/luo-yc17/Reflect-VLA

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Distillation — 1× in this paper · explained in 2 episodes
• Self-Distillation — 1× in this paper · explained in 7 episodes

Sources

• Pseudo-Simulation for Autonomous Driving
• DriveReward: A Comprehensive Dataset and Generative Vision-Language Reward Model for Autonomous Driving
• ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation
• DriveVer: Lightweight Trajectory Evaluator as Test-Time Verifier for Autonomous Driving
• DriveLMM-o1: A Step-by-Step Reasoning Dataset and Large Multimodal Model for Driving Scenario Understanding
• Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving
• AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning
• A Survey on Vision-Language-Action Models for Autonomous Driving
• DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
• End-to-End Driving with Online Trajectory Evaluation via BEV World Model
• ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
• Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation
• ReasonPlan: Unified Scene Prediction and Decision Reasoning for Closed-loop Autonomous Driving
• Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
• LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving
• AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving
• MTRDrive: Memory-Tool Synergistic Reasoning for Robust Autonomous Driving in Corner Cases
• CRISP: Compressed Reasoning via Iterative Self-Policy Distillation
• DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model
• Judge, Then Drive: A Critic-Centric Vision Language Action Framework for Autonomous Driving

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies