Saved in:
Bibliographic Details
Main Authors: Tuisov, Alexander, Vernik, Yonatan, Shleyfman, Alexander
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.18784
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912803220094976
author Tuisov, Alexander
Vernik, Yonatan
Shleyfman, Alexander
author_facet Tuisov, Alexander
Vernik, Yonatan
Shleyfman, Alexander
contents Heuristics are a central component of deterministic planning, particularly in domain-independent settings where general applicability is prioritized over task-specific tuning. This work revisits that paradigm in light of recent advances in large language models (LLMs), which enable the automatic synthesis of heuristics directly from problem definitions -- bypassing the need for handcrafted domain knowledge. We present a method that employs LLMs to generate problem-specific heuristic functions from planning tasks specified through successor generators, goal tests, and initial states written in a general-purpose programming language. These heuristics are compiled and integrated into standard heuristic search algorithms, such as greedy best-first search. Our approach achieves competitive, and in many cases state-of-the-art, performance across a broad range of established planning benchmarks. Moreover, it enables the solution of problems that are difficult to express in traditional formalisms, including those with complex numeric constraints or custom transition dynamics. We provide an extensive empirical evaluation that characterizes the strengths and limitations of the approach across diverse planning settings, demonstrating its effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2501_18784
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Successor-Generator Planning with LLM-generated Heuristics
Tuisov, Alexander
Vernik, Yonatan
Shleyfman, Alexander
Artificial Intelligence
Heuristics are a central component of deterministic planning, particularly in domain-independent settings where general applicability is prioritized over task-specific tuning. This work revisits that paradigm in light of recent advances in large language models (LLMs), which enable the automatic synthesis of heuristics directly from problem definitions -- bypassing the need for handcrafted domain knowledge. We present a method that employs LLMs to generate problem-specific heuristic functions from planning tasks specified through successor generators, goal tests, and initial states written in a general-purpose programming language. These heuristics are compiled and integrated into standard heuristic search algorithms, such as greedy best-first search. Our approach achieves competitive, and in many cases state-of-the-art, performance across a broad range of established planning benchmarks. Moreover, it enables the solution of problems that are difficult to express in traditional formalisms, including those with complex numeric constraints or custom transition dynamics. We provide an extensive empirical evaluation that characterizes the strengths and limitations of the approach across diverse planning settings, demonstrating its effectiveness.
title Successor-Generator Planning with LLM-generated Heuristics
topic Artificial Intelligence
url https://arxiv.org/abs/2501.18784