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.
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.
A novel safe task-planning framework, SafeMem, which constructs and maintains a long-term semantic graph memory of the open and dynamic environment, and substantially improves safe success rates compared to state-of-the-art VLM-driven task planners.
Si-Yuan Li, Tai-Yan Lang, Ao Yan et al.· 1 citation
An LLM-guided planning framework ADM-Planner with attention-enhanced dynamic memory shows that selective state maintenance with ADM, rather than prompt history alone, is a practical basis for long-horizon planning in changing environments.
Jia-Ping Xiao, Ping-Yuan Ji, Mir Feroskhan· 0 citations
Task planning bridges high-level instructions and executable behavior in long-horizon manipulation, yet modern Vision-Language-Action (VLA) systems often leave this intermediate structure implicit. Existing chain-of-thought (CoT) planners also tend to rely on coarse task-level annotations or serialize long reasoning tr...
Howard Lu, Shalfun Li, Porter Pan et al.· 0 citations
SAGE (Symbolic Action-Gating and Editing), a single-LLM planner built from two lightweight mechanisms: a domain-agnostic symbolic gate that blocks precondition-violating actions with typed reasons as a runtime safety monitor, and a local edit that regenerates only the failed sub-goal's suffix, keeping completed and unt...
T. Bui, Jongsul Moon, Youngouk Kim et al.· arXiv.org· 0 citations
Evidence Acquisition and Feasibility Gating (EAFG) is proposed, a framework that acquires visual evidence through VLM-generated exploratory subgoals and TAMP-based execution and applies a feasibility gate to decide whether to proceed with task planning, acquire further evidence, or halt.
Tsunehiko Tanaka, Matthew Stephenson, Alistair Macvicar et al.· 0 citations
SGG-ReflAct (Sub-Goal Guided Re flAct), a reasoning backbone that integrates sub-goals generated through a single path LLM planner into the reflection process, and BeamSGG-ReflAct, which replaces the single-path planner with a beam search based LLM planner for structured plan exploration.
Jaeho Jung, Sung-Hoon Jung· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduJul 30, 2026
From feet to fingertips — we are teaching robots intelligent whole-body control, fine dexterity, and teamwork to complete a broad range of complex tasks.