GAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning

Hugging Face Daily Papers Papers
graph-world-models llm-planning embodied-planning verification repair efficiency

Summary

This paper introduces GAVEL, a framework that uses graph world models to verify and repair long-horizon LLM planning for robotic tasks, significantly improving success rates and efficiency in simulations.

Large language models (LLMs) provide a flexible interface for long-horizon robot planning, but generated plans often fail to respect embodiment constraints, recover from planning errors, or reason effectively under partial observability. We present GAVEL, a framework for verifying and repairing long-horizon LLM planning built around an explicit graph world model. The graph represents relevant object-relations, action pre-conditions and effects, and probabilistic beliefs over unobserved object locations. This model can predict the consequences of LLM-generated actions before execution, detect violations, and repair those whose corrections follow directly from the world model. This method also reserves LLM replanning solely for errors requiring semantic reasoning. For multi-task instructions, GAVEL reasons over distributions of possible object locations to reorder remaining subtasks and minimize expected search cost. We evaluate GAVEL on BEHAVIOR-1K across 100 single long-horizon tasks and 500 multi-task instructions. With Qwen3-8B, GAVEL improves single-task success from 41.2% to 91.8% and multi-task success from 19.9% to 92.6%. Distributional belief reasoning also reduces travel distance by approximately 5.4% compared with a static variant. These improvements show that an explicit graph world model harness can substantially improve the reliability and efficiency of long-horizon embodied planning across compact and frontier hosted LLM capabilities.
Original Article
View Cached Full Text

Cached at: 09/21/26, 03:22 PM

Paper page - GAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning

Source: https://huggingface.co/papers/2609.19315

Abstract

Largelanguagemodels(LLMs)provideaflexibleinterfaceforlong-horizonrobotplanning,butgeneratedplansoftenfailtorespectembodimentconstraints,recoverfromplanningerrors,orreasoneffectivelyunderpartialobservability.WepresentGAVEL,aframeworkforverifyingandrepairinglong-horizonLLMplanningbuiltaroundanexplicitgraphworldmodel.Thegraphrepresentsrelevantobject-relations,actionpre-conditionsandeffects,andprobabilisticbeliefsoverunobservedobjectlocations.ThismodelcanpredicttheconsequencesofLLM-generatedactionsbeforeexecution,detectviolations,andrepairthosewhosecorrectionsfollowdirectlyfromtheworldmodel.ThismethodalsoreservesLLMreplanningsolelyforerrorsrequiringsemanticreasoning.Formulti-taskinstructions,GAVELreasonsoverdistributionsofpossibleobjectlocationstoreorderremainingsubtasksandminimizeexpectedsearchcost.WeevaluateGAVELonBEHAVIOR-1Kacross100singlelong-horizontasksand500multi-taskinstructions.WithQwen3-8B,GAVELimprovessingle-tasksuccessfrom41.2%to91.8%andmulti-tasksuccessfrom19.9%to92.6%.Distributionalbeliefreasoningalsoreducestraveldistancebyapproximately5.4%comparedwithastaticvariant.Theseimprovementsshowthatanexplicitgraphworldmodelharnesscansubstantiallyimprovethereliabilityandefficiencyoflong-horizonembodiedplanningacrosscompactandfrontierhostedLLMcapabilities.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2609\.19315

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

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.19315 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.19315 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.19315 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