Successor-Generator Planning with LLM-generated Heuristics

TL;DR

This paper introduces a novel approach using large language models to automatically generate heuristics for deterministic planning, enabling effective solutions across diverse benchmarks without handcrafted domain knowledge.

Contribution

It presents a method that synthesizes problem-specific heuristics from planning tasks using LLMs, integrating them into standard search algorithms for improved performance.

Findings

Achieves competitive or state-of-the-art results on planning benchmarks.

Enables solving problems with complex numeric constraints and custom dynamics.

Demonstrates the effectiveness of LLM-generated heuristics across diverse planning scenarios.

Abstract

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.