Structured Program Synthesis using LLMs: Results and Insights from the IPARC Challenge

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Surana, Shraddha, Srinivasan, Ashwin, Bain, Michael
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913903351431168
author Surana, Shraddha
Srinivasan, Ashwin
Bain, Michael
author_facet Surana, Shraddha
Srinivasan, Ashwin
Bain, Michael
contents The IPARC Challenge, inspired by ARC, provides controlled program synthesis tasks over synthetic images to evaluate automatic program construction, focusing on sequence, selection, and iteration. This set of 600 tasks has resisted automated solutions. This paper presents a structured inductive programming approach with LLMs that successfully solves tasks across all IPARC categories. The controlled nature of IPARC reveals insights into LLM-based code generation, including the importance of prior structuring, LLMs' ability to aid structuring (requiring human refinement), the need to freeze correct code, the efficiency of code reuse, and how LLM-generated code can spark human creativity. These findings suggest valuable mechanisms for human-LLM collaboration in tackling complex program synthesis.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13820
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Structured Program Synthesis using LLMs: Results and Insights from the IPARC Challenge
Surana, Shraddha
Srinivasan, Ashwin
Bain, Michael
Software Engineering
Artificial Intelligence
Programming Languages
The IPARC Challenge, inspired by ARC, provides controlled program synthesis tasks over synthetic images to evaluate automatic program construction, focusing on sequence, selection, and iteration. This set of 600 tasks has resisted automated solutions. This paper presents a structured inductive programming approach with LLMs that successfully solves tasks across all IPARC categories. The controlled nature of IPARC reveals insights into LLM-based code generation, including the importance of prior structuring, LLMs' ability to aid structuring (requiring human refinement), the need to freeze correct code, the efficiency of code reuse, and how LLM-generated code can spark human creativity. These findings suggest valuable mechanisms for human-LLM collaboration in tackling complex program synthesis.
title Structured Program Synthesis using LLMs: Results and Insights from the IPARC Challenge
topic Software Engineering
Artificial Intelligence
Programming Languages
url https://arxiv.org/abs/2506.13820