# Successor-Generator Planning with LLM-generated Heuristics

Source: [Successor-Generator Planning with LLM-generated Heuristics](<https://www.sota2.com/research/paper/68fa7a601e209131cea82b60>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-10T05:00:01.276Z

Authors: Alexander Tuisov, Yonatan Vernik, Alexander Shleyfman

Published: 2025-01-30T22:21:12.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Numeric Planning on IPC Numeric & Custom Planning Domains 2023 (Evaluation set)](<https://www.sota2.com/research/sota/numeric-planning-on-ipc-numeric-and-custom-planning-domains-2023-evaluation-set.md>): Numeric Planning; IPC Numeric & Custom Planning Domains 2023 (Evaluation set); Block Grouping Score: 19.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2501.18784>)

[PDF](<https://arxiv.org/pdf/2501.18784.pdf>)