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%.
- Products
- GAVEL
- AI models
- Qwen3-8BBEHAVIOR-1K
From the original article
1 min read at huggingface.co
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.
By Ruiyang Wang, Hao-Lun Hsu, Swarajh Mehta · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.