arXiv AI By Ruiyang Wang, Hao-Lun Hsu, Swarajh Mehta, Jiwoo Kim, Zhihao Dou, Miroslav Pajic

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

Read the original on arXiv AI →

GAVEL is a framework that uses an explicit graph world model to verify and repair long‑horizon plans generated by large language models (LLMs). The graph encodes object relations, action pre‑conditions and effects, and probabilistic beliefs about unobserved object locations, allowing the system to predict action outcomes, detect violations, and repair them before execution. In experiments on BEHAVIOR‑1K, GAVEL boosts single‑task success from 41.2 % to 91.8 % and multi‑task success from 19.9 % to 92.6 %, while also reducing travel distance by about 5.4 % compared with a static variant.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computation and Language
Oct 23

MemPlan: Memory-Conditioned PDDL Planning for Partially Observable Text Environments

MemPlan is a memory‑conditioned PDDL planning framework designed for partially observable interactive text environments. It keeps the PDDL domain fixed and reconstructs the problem at each step using parsed observations, candidate hypotheses, and interaction memory, employing positive graph memory to assign relevance‑based action costs and negative memory to record refuted assumptions as exclusion constraints. Experiments on TextWorld, ALFWorld, and Robotouille demonstrate that MemPlan improves task completion and step efficiency over language‑only and PDDL‑aware baselines while significantly reducing online token cost compared with LLM‑planning baselines such as ReAct, and its fine‑tuned interface generalizes across task types without task‑specific fine‑tuning.

By Tengwei Song, Robert Hoehndorf