AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

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

Zhenlong Yuan, Chengxuan Qian, Jing Tang, Rui Chen, Zijian Song, Lei Sun, Xiangxiang Chu, Yujun Cai, Dapeng Zhang, Shuo Li

ICLR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models

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 SFT on nuScenesR2-6K CoT data (ablation)Qwen2.5-VL-7B · nuScenes (L2 error)avg L2 error (m): 1.45 -> 0.27Improved
add RL stage after SFT (two-stage vs RL only) (ablation)AutoDrive-R² 7B · nuScenes (L2 error)avg L2 error (m): RL-only worse than SFT by 22.2%; SFT+RL 0.19Improved
add four-step reasoning structure to CoT data (ablation)AutoDrive-R² 7B · nuScenes (L2 error)avg L2 error (m): 0.25 -> 0.19Improved
add self-reflection step to CoT data (ablation)AutoDrive-R² 7B · nuScenes (L2 error)avg L2 error (m): 0.23 -> 0.19Improved
add spatial alignment reward r_pos (ablation)AutoDrive-R² 7B · nuScenes (L2 error)avg L2 error (m): 0.53 -> 0.19Improved
add steering reward r_ste (ablation)AutoDrive-R² 7B · nuScenes (L2 error)avg L2 error (m): 0.21 -> 0.19Improved
add velocity reward r_vel (ablation)AutoDrive-R² 7B · nuScenes (L2 error)avg L2 error (m): 0.22 -> 0.19Improved
add temporal smoothness reward r_tem (ablation)AutoDrive-R² 7B · nuScenes (L2 error)avg L2 error (m): 0.24 -> 0.19Improved
use uniform instead of decaying reward weights (ablation)AutoDrive-R² 7B · nuScenes (L2 error)avg L2 error (m): 0.22 -> 0.19Improved
set KL coefficient beta to 0.04 vs 0.02 or 0.06 (ablation)AutoDrive-R² 7B · nuScenes (L2 error)avg L2 error (m): 0.21 (0.02), 0.20 (0.06) -> 0.19 (0.04)Improved
increase GRPO generations G from 2 to 6 (ablation)AutoDrive-R² 7B · nuScenes (L2 error)avg L2 error (m): 0.23 -> 0.19Improved
increase GRPO generations G from 6 to 8 (ablation)AutoDrive-R² 7B · nuScenes (L2 error)avg L2 error (m)No clear effect

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