AI Paper Atlas

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

Guide, Think, Act: Interactive Embodied Reasoning for Vision-Language-Action Model

Yiran Ling, Qing Lian, Jinghang Li, Qing Jiang, TianMing Zhang, Xiaoke Jiang, Chuanxiu Liu, Jie Liu, Lei Zhang

ECCV 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
remove vision CoT field (visual grounding) (ablation)GTA-VLA · SimplerEnv WidowXsuccess rate (%): 81.2 -> 66.7Improved
add task CoT field (task decomposition) (ablation)GTA-VLA · SimplerEnv WidowXsuccess rate (%): 68.8 -> 81.2Improved
add robot CoT field (motion sketch) (ablation)GTA-VLA · SimplerEnv WidowXsuccess rate (%): 78.1 -> 81.2Improved
use structured CoT fields instead of free-form CoT (ablation)GTA-VLA · SimplerEnv WidowXsuccess rate (%): 65.6 -> 81.2Improved
add visual point guide to dense instruction (ablation)GTA-VLA · SimplerEnv-Plus distractor ambiguitysuccess rate (%): 37.5 -> 54.2Improved
add visual box guide to dense instruction (ablation)GTA-VLA · SimplerEnv-Plus unseen object ambiguitysuccess rate (%): 27.8 -> 56.9Improved
add visual box guide instead of none on distractor ambiguity (ablation)GTA-VLA · SimplerEnv-Plus distractor ambiguitysuccess rate (%): 37.5 -> 43.7Improved
add trace guide (ablation)GTA-VLA · SimplerEnv-Plus obstacle-avoidance taskssuccess rate (%): 27.8 -> 30.5Improved
add explicit spatial reasoning and guidance interfaceGTA-VLA vs X-VLA · SimplerEnv-Plus OODavg success rate (%): 52.3 -> 61.4Improved
add spatial reasoning to policyGTA-VLA vs X-VLA · LIBEROavg success rate (%): 98.1 -> 98.6No 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