AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

LAGEA: Language Guided Embodied Agents for Robotic Manipulation

Abdul Monaf Chowdhury, Akm Moshiur Rahman Mazumder, Safaeid Hossain Arib, Rabeya Akter

ICML 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Embodied agent learning · 0 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 structured schema-constrained feedback (ablation)LaGEA · MT10 tasksaverage success rate (%): 78.89 -> 98.89Improved
add LaGEA keyframe selection (vs uniform) (ablation)LaGEA · MT10 five observable tasksaverage success rate (%): 67.33 -> 80Improved
add LaGEA keyframe selection (vs random) (ablation)LaGEA · MT10 five observable tasksaverage success rate (%): 68 -> 80Improved
add learned feedback-vision alignment (ablation)LaGEA · button-press-topdown-v2 observablesuccess rate (%): 20 -> 93.33Improved
add adaptive failure-aware rho (ablation)LaGEA · button-press-topdown-v2 observablesuccess rate (%): 13.33 -> 93.33Improved
add delta (potential-based) rewards (ablation)LaGEA · button-press-topdown-v2 observablesuccess rate (%): 30 -> 93.33Improved
add goal and feedback delta terms to adaptive rho (ablation)LaGEA · drawer-open-v2 observablesuccess rate (%): 0 -> 100Improved
replace weaker VLM with Qwen-2.5-VL-3B (ablation)LaGEA · MT10 five observable tasksaverage success rate (%): 56 -> 80Improved
replace LIV text encoder with GPT-2 feedback encoding (ablation)LaGEA · MT10 five observable tasksaverage success rate (%): 72.67 -> 80Improved
train on one viewpoint, test on unseen overhead cameraLaGEA · MT10 five observable tasksaverage success rate (%): 80 -> 79.33No clear effect
add LaGEA language-feedback reward over FuRLLaGEA · Meta-World MT10 hidden fixed goalaverage success rate (%): 76.0 -> 80.0Improved
add LaGEA language-feedback reward over FuRLLaGEA · Robotic Fetchaverage success rate (%): 44.17 -> 51.67Improved

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