AI Paper Atlas

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

RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks

Ruiying Li, Yunlang Zhou, Yuyao Zhu, Kylin Chen, Sukai Wang, Kongtao Hu, Minhui Yu, Bowen Jiang, Jiayao Ma, Zhan Su, Yongjian Shen, Yang Yang and 4 more

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Multimodal prompt-driven manipulation · 57 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 more rollout iterations (1 to 5, 50 samples each) of EAP data (ablation)RoboClaw forward policy · Forward policy, Body Lotionsuccess rate: 21/50 -> 43/50Improved
add more rollout iterations (1 to 5, 50 samples each) of EAP data (ablation)RoboClaw forward policy · Forward policy, Primersuccess rate: 23/50 -> 40/50Improved
add more rollout iterations (1 to 5, 50 samples each) of EAP data (ablation)RoboClaw forward policy · Forward policy, Lipsticksuccess rate: 2/50 -> 23/50Improved
add more rollout iterations (1 to 5, 50 samples each) of EAP data (ablation)RoboClaw forward policy · Forward policy, Tissue Wipesuccess rate: 11/50 -> 26/50Improved
use EAP autonomous collection instead of manual demonstrations and resetsRoboClaw · Data collection (4 scenes)human time: manual baseline requires 2.16x more human timeImproved
use EAP autonomous collection instead of manualRoboClaw · Data collection rolloutshuman intervention: manual baseline requires 8.04x more human interventionImproved
use RoboClaw agent monitoring and recovery vs pi0.5 baseline and product-of-subtask baselineRoboClaw · Vanity table organizationsuccess rate: 25% higher success rateImproved
add human intervention requests on abnormal situationsRoboClaw · Human burdenhuman burden: reduces human burden by 53.7%Improved
add learned recovery policies from rollouts to policy libraryRoboClaw · Long-horizon executionsuccess rateImproved

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