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

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

20 Jan 2025arXiv:2501.17167archive 2025-07-28

Yaojie Hu, Qiang Zhou, Qihong Chen, Xiaopeng Li, Linbo Liu, Dejiao Zhang, Amit Kachroo, Talha Oz, Omer Tripp

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.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Code GenerationHumanEvalLanguage ModelingLanguage ModellingLarge Language ModelProgram Synthesis

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Code Generation HumanEval QualityFlow (Sonnet-3.5) Pass@1 98.8 #3 of 8 Archive leaderboard report
Code Generation MBPP QualityFlow (Sonnet-3.5) Accuracy 94.2 #2 of 99 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections