Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation

Hugging Face Daily Papers Papers
robotics world-action-model manipulation visual-subgoals in-context-learning hierarchical-planning imitation-learning

Summary

The paper proposes ViGAR, a hierarchical world-action model for long-horizon compositional robotic manipulation that factorizes tasks into a visual subgoal planner and a subgoal executor, achieving 82.00% and 67.02% success on the RoboTwin Clean2Random benchmark and outperforming the strongest baseline by 12.86 percentage points.

Long-horizon compositional manipulation has become increasingly important for real-world robot deployment, where a single task involves multiple coordinated subtasks. Existing world-action models (WAMs) jointly predict short-horizon visual futures and actions, but typically lack explicit subtask-level reasoning. We propose Visual Goal-conditioned Action Reasoning (ViGAR), a hierarchical framework that factorizes manipulation into a visual subgoal planner and a subgoal executor. Given the current observation and global instruction, the subgoal planner predicts a visual subgoal for the next subtask. The subgoal executor then jointly generates future visual trajectories and actions conditioned on the predicted subgoal. Both components share a pretrained world-model representation, enabling task-level planning and action generation to benefit from common physical knowledge. Moreover, our framework naturally supports in-context learning: using a global goal image as context can induce different subtask decompositions and behaviors without parameter updates. On the RoboTwin Clean2Random benchmark, ViGAR achieves 82.00% and 67.02% success rates under the Clean and Random settings, respectively, surpassing the strongest baseline by 12.86 percentage points in average success rate. Real-world robot experiments on five compositional and two in-context learning tasks further confirm the effectiveness of ViGAR.
Original Article
View Cached Full Text

Cached at: 10/08/26, 12:16 PM

Paper page - Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation

Source: https://huggingface.co/papers/2610.02368 Published on Oct 1

·

Submitted byhttps://huggingface.co/yfdeng10

yfdengon Oct 8

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Long-horizoncompositionalmanipulationhasbecomeincreasinglyimportantforreal-worldrobotdeployment,whereasingletaskinvolvesmultiplecoordinatedsubtasks.Existingworld-actionmodels(WAMs)jointlypredictshort-horizonvisualfuturesandactions,buttypicallylackexplicitsubtask-levelreasoning.WeproposeVisualGoal-conditionedActionReasoning(ViGAR),ahierarchicalframeworkthatfactorizesmanipulationintoavisualsubgoalplannerandasubgoalexecutor.Giventhecurrentobservationandglobalinstruction,thesubgoalplannerpredictsavisualsubgoalforthenextsubtask.Thesubgoalexecutorthenjointlygeneratesfuturevisualtrajectoriesandactionsconditionedonthepredictedsubgoal.Bothcomponentsshareapretrainedworld-modelrepresentation,enablingtask-levelplanningandactiongenerationtobenefitfromcommonphysicalknowledge.Moreover,ourframeworknaturallysupportsin-contextlearning:usingaglobalgoalimageascontextcaninducedifferentsubtaskdecompositionsandbehaviorswithoutparameterupdates.OntheRoboTwinClean2Randombenchmark,ViGARachieves82.00%and67.02%successratesundertheCleanandRandomsettings,respectively,surpassingthestrongestbaselineby12.86percentagepointsinaveragesuccessrate.Real-worldrobotexperimentsonfivecompositionalandtwoin-contextlearningtasksfurtherconfirmtheeffectivenessofViGAR.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2610\.02368

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper1

#### DAGroup-PKU/ViGAR Robotics• Updatedabout 21 hours ago

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.02368 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.02368 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

World Action Modeling with Progressive Visual Planning

arXiv cs.AI

ProWAM is a progressive world action model that jointly predicts robot actions and an ordered sequence of sparse visual sub-goals, enabling efficient long-horizon control without dense video generation. It achieves state-of-the-art results on LIBERO-Plus and RoboTwin, plus 70% zero-shot real-world success.

World Value Models for Robotic Manipulation

Hugging Face Daily Papers

The paper presents World Value Model (WVM), a generalist robotic value model that combines world models with value estimation to accurately assess task progression and improve robotic policy learning from mixed-quality data, achieving state-of-the-art results on standard benchmarks and a new suboptimal data benchmark.