AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation

Yibin Liu, Yaxing Lyu, Daqi Gao, Zhixuan Liang, Weiliang Tang, Shilong Mu, Xiaokang Yang, Mingyu Ding, Yao Mu

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Reinforcement learning for visual reasoning · 8 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 GRPO RL stage after SFT (ablation)SFT-only PRIMO · PRIMO Bench (7-split average)MRA: 79.35 -> 85.28Improved
add SFT stage before RL (ablation)RL-only PRIMO · PRIMO Bench (7-split average)MRA: 76.72 -> 85.28Improved
add RL after SFT on Real Humanoid cross-environment (ablation)SFT-only PRIMO · PRIMO Bench (Real Humanoid)MRA: 67.30 -> 72.32Improved
apply SFT to base model (ablation)Qwen2.5-VL-7B · PRIMO Bench (7-split average)MRA: 67.46 -> 79.35Improved
apply SFT only (ablation)Qwen2.5-VL-7B · RoboFailaccuracy (%): 57.6 -> 51.0Hurt
apply RL (GRPO) after SFT (ablation)PRIMO (SFT) · RoboFailaccuracy (%): 51.0 -> 63.0Improved
add SFT before RL on failure detection (ablation)PRIMO (RL) · RoboFailaccuracy (%): 63.0 -> 67.0Improved
add initial state image to current image (ablation)I_curr only · PRIMO Bench (avg MAE)MAE: 59.50 -> 46.50Improved
replace current-only input with video sequence (ablation)I_curr only · PRIMO Bench (avg MAE)MAE: 59.50 -> 36.61Improved
add both boundary images to video input (ablation)V_seq only · PRIMO Bench (avg MAE)MAE: 36.61 -> 31.43Improved
add video sequence to boundary-state images on Behavior (ablation)I_init + I_curr · BehaviorMAE: 49.59 -> 22.73Improved
add initial image to V_seq + I_curr on AgiBot (ablation)V_seq + I_curr · AgiBotMAE: 25.04 -> 29.39Hurt

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