Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Semantic Partial Grounding via LLMs

Giuseppe Canonaco, Alberto Pozanco, Daniel Borrajo

TL;DR

SPG-LLM is proposed, 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.

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.

Semantic Partial Grounding via LLMs

TL;DR

SPG-LLM is proposed, 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.

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.
Paper Structure (14 sections, 2 figures, 1 table, 1 algorithm)

This paper contains 14 sections, 2 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Background
  3. Proposed Approach
  4. Evaluation
  5. Experimental Setting
  6. Benchmark.
  7. Approaches.
  8. Metrics.
  9. Reproducibility.
  10. Results
  11. Grounding Results.
  12. Solving Results.
  13. Conclusions and Future Work
  14. Prompt Template

Figures (2)

  • Figure 1: Number of grounded actions (Figures \ref{['fig:fg_vs_spg_ops']} and \ref{['fig:ploi_vs_spg_ops']}) and plan cost (Figures \ref{['fig:fg_vs_spg_cost']} and \ref{['fig:ploi_vs_spg_cost']}) produced by each baseline ($y$-axis) and SPG-LLM ($x$-axis). Each point is a problem, with markers indicating the domain. Points above the diagonal indicate SPG-LLM have better performance. Points within the red dashed lines indicate cases where the approaches either failed to solve the grounded task within the time and memory limits, or produced a grounding that resulted in a plan not valid for the original task.
  • Figure 2: Prompt Template