GAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning
GAVEL framework uses graph world models to improve LLM-based robot planning success rates from ~41% to ~92%.
GAVEL is a framework for verifying and repairing long-horizon LLM planning using an explicit graph world model representing object relations and probabilistic beliefs. Tested on the BEHAVIOR-1K benchmark with the Qwen3-8B model, GAVEL significantly improves task success rates for both single and multi-task instructions. The system reserves LLM replanning for errors requiring semantic reasoning and uses belief reasoning to optimize subtask ordering.
- GAVEL uses an explicit graph world model to verify and repair long-horizon LLM planning.
- The framework improves single-task success from 41.2% to 91.8% with Qwen3-8B.
- Multi-task success increases from 19.9% to 92.6% using GAVEL.
- Distributional belief reasoning reduces expected travel distance by about 5.4%.
Full article196 words · extracted from huggingface.co · click to collapse
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.
Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/papers/2609.19315