AI Paper Atlas

Research map / Large language models / Reasoning and chain of thought

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

Zhaohong Liu, Hao Ye, Xianlin Zhang, Mengshi Qi

ECCV 2026 · Large language models › Reasoning and chain of thought · approach: RL with verifiable rewards for reasoning · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add accuracy-reward GRPO after warm-up SFT (ablation)Qwen3-VL-8B SFT · DriveLMM-o1MCQ (%): 62.86 -> 64.49Improved
add multi-dimensional verifier rewards to single-turn GRPO (ablation)Qwen3-VL-8B GRPO · DriveLMM-o1MCQ (%): 64.49 -> 67.46Improved
add multi-turn interaction with step-decay penalty (ablation)Qwen3-VL-8B GRPO + verifier · DriveLMM-o1MCQ (%): 67.46 -> 76.54Improved
add multi-turn interaction with step-decay penalty (ablation)Qwen3-VL-8B GRPO + verifier · DriveLMM-o1Overall reasoning (%): 75.10 -> 80.48Improved
add multi-turn interaction with step-decay penalty (ablation)Qwen3-VL-8B GRPO + verifier · DriveLMM-o1Risk assessment (%): 75.30 -> 81.63Improved
add warm-up SFT on DriveLMM-o1 CoT data (ablation)Qwen3-VL-8B · DriveLMM-o1MCQ (%): 55.54 -> 62.86Mixed
add latent alignment loss (Latent Thought Distillation) to CoT-free student (ablation)Qwen3-VL-8B (SFT) CoT-free · DriveLMM-o1MCQ (%): 61.73 -> 68.59Improved
distill into CoT-free student instead of running teacher with CoT (ablation)Ours-Teacher · DriveLMM-o1Avg. inference time (ms): 3482 -> 416Improved
distill into CoT-free student instead of running teacher with CoTOurs-Teacher · DriveLMM-o1MCQ (%): 76.54 -> 68.59Hurt
remove CoT from Qwen3-VL-8B (SFT) at inferenceQwen3-VL-8B (SFT) · DriveLMM-o1MCQ (%): 62.86 -> 61.73Hurt
use verifier-critique multi-turn RL instead of external tool calls (AgentThink)Ours-Teacher vs AgentThink · DriveLMM-o1Avg. inference time (ms): 5416 -> 3482Improved
tool-free multi-turn RL teacher versus tool-augmented AgentThinkOurs-Teacher vs AgentThink · DriveLMM-o1MCQ (%): 71.35 -> 76.54Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy