AI Paper Atlas

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

E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation

Wen Ye, Peiyan Li, Tingyu Yuan, Yuan Xu, Xiangnan Wu, Chaoyang Zhao, Jing Liu, Nianfeng Liu, Yan Huang, Liang Wang

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Memory and subgoal-based manipulation · 1 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 E-TTSE-CoT · SimplerEnv WidowXaverage success rate: 6.67 -> 39.81Improved
add E-TTS instead of RoboMonkeyE-CoT · SimplerEnv WidowXaverage success rate: 26.38 -> 39.81Improved
add feedback generation (ablation)E-TTS · SimplerEnv WidowXaverage success rate: 25.04 -> 39.81Improved
add reasoning scaling to action scaling (ablation)E-TTS · SimplerEnv WidowXaverage success rate: 26.39 -> 39.81Improved
add action scaling to reasoning scaling (ablation)E-TTS · SimplerEnv WidowXaverage success rate: 30.56 -> 39.81Improved
add joint reasoning-action scoring (ablation)E-TTS · SimplerEnv WidowXaverage success rate: 31.13 -> 39.81Improved
add history buffer (ablation)E-TTS · SimplerEnv WidowXaverage success rate: 31.94 -> 39.81Improved
add epsilon-greedy exploration (ablation)E-TTS · SimplerEnv WidowXaverage success rate: 36.11 -> 39.81Improved
increase history length K from 1 to 10 (ablation)E-TTS · SimplerEnv WidowXsuccess rate: 37.50 -> 58.33Improved
increase history length K from 10 to 20 (ablation)E-TTS · SimplerEnv WidowXsuccess rate: 58.33 -> 45.83Hurt
increase threshold eta from 0.1 to 0.5 (ablation)E-TTS · SimplerEnv WidowXsuccess rate: 70.83 -> 33.33Hurt
increase epsilon from 0.1 to 0.7 (ablation)E-TTS · SimplerEnv WidowXsuccess rate: 54.17 -> 33.33Hurt

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