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

Papers

arxiv:2609.19315

Published on Sep 16

· Submitted by

Ruiyang Wang on Sep 21

· Duke University

Upvote

3

Authors:

Ruiyang Wang ,

,

,

,

,

Abstract

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.

View arXiv page View PDF Add to collection

Community

ruiyangw

Paper author Paper submitter 1 day ago

This comment has been hidden

librarian-bot

about 13 hours ago

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

• Plan Along the Way: Event-Triggered Foundation-Model Planning for TAMP Execution in Partially Observable Manipulation (2026)

• HarnessWAM: Bridging Prediction and Deliberation in World Action Models (2026)

• Bridging Semantics and Physics with Constrained LLMs for Safe and Trustworthy Robotic Manipulation (2026)

• From Failures to Supervision: DynamicEnvPlan for Robust Long-Horizon Embodied Planning (2026)

• Evidence-Gated Task and Motion Planning with Vision-Language Models (2026)

• CLAMP: Constrained Decoding for Vision-Language Embodied Planning (2026)

• Meta-Ctrl: Guaranteed Plan Generation by Decoupling Syntactic and Semantic Constraints (2026)

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on HF Mirror checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

Upvote

3

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 paper 0

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 paper 0

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 paper 0

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 paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.