Semantic Partial Grounding via LLMs

TL;DR

This paper introduces SPG-LLM, a novel method that leverages large language models to analyze planning domain files, heuristically reducing grounding size and significantly speeding up the process without sacrificing plan quality.

Contribution

The paper presents a new approach using LLMs for partial grounding in classical planning, effectively reducing grounding complexity by analyzing domain descriptions.

Findings

Achieves orders-of-magnitude faster grounding times.

Maintains or improves plan costs in tested benchmarks.

Reduces grounding size significantly.

Abstract

Grounding is a critical step in classical planning, yet it often becomes a computational bottleneck due to the exponential growth in grounded actions and atoms as task size increases. Recent advances in partial grounding have addressed this challenge by incrementally grounding only the most promising operators, guided by predictive models. However, these approaches primarily rely on relational features or learned embeddings and do not leverage the textual and structural cues present in PDDL descriptions. We propose SPG-LLM, which uses LLMs to analyze the domain and problem files to heuristically identify potentially irrelevant objects, actions, and predicates prior to grounding, significantly reducing the size of the grounded task. Across seven hard-to-ground benchmarks, SPG-LLM achieves faster grounding-often by orders of magnitude-while delivering comparable or better plan costs in some domains.