# CritiqueDriveVLM: From Verifier-Guided Reinforcement Learning to Latent Thought Distillation for Autonomous Driving

arXiv: https://arxiv.org/abs/2607.04179 · HTML: https://mlsanity.com/paper/2607.04179/

## Key facts

- Cited by 2 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 55 of its 64 references that are in the map.
- First posted on arXiv 5 Jul 2026.

## Placed in

- LLM reasoning / [Chain-of-thought reasoning for driving](https://mlsanity.com/lr/chain-of-thought-reasoning-for-driving/)
- Multimodal LLMs / vision-language models / [Driving VLMs and open-vocabulary detection](https://mlsanity.com/mllm/driving-vlms-and-open-vocabulary-detection/)
- 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 55)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation](https://mlsanity.com/paper/2005.04259/) (2020)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [LLaVA-CoT: Let Vision Language Models Reason Step-by-Step](https://mlsanity.com/paper/2411.10440/) (2024)
- [LMDrive: Closed-Loop End-to-End Driving with Large Language Models](https://mlsanity.com/paper/2312.07488/) (2023)
- [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)

## Built on by (most cited first, 2 of 2)

- [SimWAM: A Simple World Action Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2608.07468/) (2026)
- [Drive by Hindsight and Foresight: Tool-Grounded Synergistic Reasoning over Hierarchical Memory for Autonomous Driving](https://mlsanity.com/paper/2609.08217/) (2026)

## Abstract (arXiv)

End-to-end Vision-Language Models (VLMs) show immense potential in autonomous driving. However, standard Supervised Fine-Tuning (SFT) often suffers from reasoning hallucinations and conservative biases. While traditional tool-augmented frameworks and Chain-of-Thought (CoT) approaches mitigate these issues, they incur exorbitant token consumption and unacceptable latency, rendering real-time deployment impractical. To resolve this reliability-efficiency trade-off, we propose CritiqueDriveVLM, a novel unified three-stage framework internalizing reasoning directly into the VLM. First, we introduce Critique-Driven Multi-Turn Reinforcement Learning (RL) guided by a multi-dimensional verifier. By providing granular scalar feedback and a multi-turn penalty, we force the policy to internalize logical deduction, cultivating a robust System-2 Teacher that achieves high accuracy without fragile external tools. Subsequently, we propose Latent Thought Distillation to overcome the latency bottleneck. By aligning the Student's latent representations with the Teacher's fully converged reasoning states, we compress deep logical capabilities into a fast, CoT-free System-1 Student. Extensive experiments on the widely-used DriveLMM-01 benchmark demonstrate remarkable improvements. Compared to the base model, our tool-free Teacher significantly boosts Multiple Choice Quality (MCQ) from 55.54% to a state-of-the-art 76.54%. Crucially, our distilled Student preserves competitive reasoning depth while drastically minimizing generation length to an average of merely 28 tokens. This slashes inference latency by 88% (from 3482 ms to 416 ms), paving a highly robust pathway for low-latency autonomous driving.Our source code is available at https://github.com/MICLAB-BUPT/CritiqueDriveVLM.