QualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality Checks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Yaojie, Zhou, Qiang, Chen, Qihong, Li, Xiaopeng, Liu, Linbo, Zhang, Dejiao, Kachroo, Amit, Oz, Talha, Tripp, Omer
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909550889664512
author Hu, Yaojie
Zhou, Qiang
Chen, Qihong
Li, Xiaopeng
Liu, Linbo
Zhang, Dejiao
Kachroo, Amit
Oz, Talha
Tripp, Omer
author_facet Hu, Yaojie
Zhou, Qiang
Chen, Qihong
Li, Xiaopeng
Liu, Linbo
Zhang, Dejiao
Kachroo, Amit
Oz, Talha
Tripp, Omer
contents We introduce QualityFlow, a dynamic agentic workflow for program synthesis. Given the English description of a programming problem and a set of unit tests, the model's goal is to synthesize the correct program that solves the problem and passes the tests. QualityFlow includes large language model (LLM) agents resembling a software development team, including code generation, testing, and self-debugging. We propose the LLM Quality Checker, which explicitly "imagines" whether the synthesized programs' execution would conform to the unit tests. The Quality Checks dynamically control the workflow, including actions to submit the final answer, clarify the problem statement, and revert previous workflow steps. Our experiments show that the Quality Checker can precisely accept any correct program, mitigate faulty synthesized tests, and prevent potential workflow deviation. QualityFlow establishes the state-of-the-art results on four program synthesis benchmarks: MBPP, HumanEval, and stricter evaluations from MBPP-EvalPlus and HumanEval-EvalPlus.
format Preprint
id arxiv_https___arxiv_org_abs_2501_17167
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle QualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality Checks
Hu, Yaojie
Zhou, Qiang
Chen, Qihong
Li, Xiaopeng
Liu, Linbo
Zhang, Dejiao
Kachroo, Amit
Oz, Talha
Tripp, Omer
Software Engineering
Artificial Intelligence
We introduce QualityFlow, a dynamic agentic workflow for program synthesis. Given the English description of a programming problem and a set of unit tests, the model's goal is to synthesize the correct program that solves the problem and passes the tests. QualityFlow includes large language model (LLM) agents resembling a software development team, including code generation, testing, and self-debugging. We propose the LLM Quality Checker, which explicitly "imagines" whether the synthesized programs' execution would conform to the unit tests. The Quality Checks dynamically control the workflow, including actions to submit the final answer, clarify the problem statement, and revert previous workflow steps. Our experiments show that the Quality Checker can precisely accept any correct program, mitigate faulty synthesized tests, and prevent potential workflow deviation. QualityFlow establishes the state-of-the-art results on four program synthesis benchmarks: MBPP, HumanEval, and stricter evaluations from MBPP-EvalPlus and HumanEval-EvalPlus.
title QualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality Checks
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2501.17167