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

• URL: http://arxiv.org/abs/2501.17167v2
• Date: Mon, 24 Mar 2025 19:10:04 GMT
• Title: QualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality Checks
• Abstract summary: QualityFlow is a dynamic agentic workflow for program synthesis.<n>The Quality Checker can precisely accept any correct program, faulty synthesized tests, and prevent potential workflow deviation.
• Score: 14.251006141747913
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Benchmarking the Titans: A Multi-Dimensional Empirical Evaluation of LLM Code Generation Quality in the .NET Ecosystem [41.99844472131922]
  Existing benchmarks reduce evaluation to a single Pass@k metric, which obscures critical trade-offs between functional correctness and structural quality.<n>This paper presents an automated, multi-dimensional evaluation framework for C# code generation, applying it to four state-of-the-art Large Language Model (LLM)<n>We conduct a controlled experiment across 85 algorithmic tasks derived from HumanEval, generating and evaluating 340 solutions in total, in which each solution is assessed across three independent dimensions.
  arXiv  Detail & Related papers  (2026-08-23T17:59:19Z)
• TTHE: Test-Time Harness Evolution [50.26245555541721]
  Existing approaches optimize such harnesses before deployment, searching training or development data for a fixed agent workflow that is then frozen at test time.<n>We ask whether the harness can instead be optimized during evaluation itself, using only the unlabeled execution traces the agent produces on the test inputs.<n>During evaluation, TTHE maintains a population of candidate harnesses and refines them through an agentic proposer that reasons over their execution traces.<n>A judge then commits an improved harness from execution-derived proxy signals, and the selected program persists to govern subsequent inputs.
  arXiv  Detail & Related papers  (2026-07-09T05:53:39Z)
• Towards Evaluation of Implicit Software World Models in Coding LLMs [3.4011650749358786]
  We take a step toward a broader evaluation by shifting the observable axis to execution resources.<n>We use SWE-bench Verified as the source of data to hold the test close to real-world software engineering tasks.
  arXiv  Detail & Related papers  (2026-06-25T08:02:32Z)
• The Rise of Agentic Testing: Multi-Agent Systems for Robust Software Quality Assurance [0.0]
  Current AI-based test generators produce invalid, redundant, or non-executable tests due to lack of execution aware feedback.<n>This paper introduces a closed-loop, self-correcting system in which a Test Generation Agent, an Execution and Analysis Agent, and a Review and Optimization Agent collaboratively generate, execute, analyze, and refine tests.
  arXiv  Detail & Related papers  (2026-01-05T18:20:14Z)
• Evaluating Software Process Models for Multi-Agent Class-Level Code Generation [5.545076518491288]
  Large Language Models (LLMs) are increasingly used to automate software development.<n>This work examines how process structure and role shape multi-agent specialization for class-level code generation.
  arXiv  Detail & Related papers  (2025-11-12T22:53:12Z)
• TDFlow: Agentic Workflows for Test Driven Software Engineering [9.028820294564566]
  TDFlow frames repository-scale software engineering as a test-resolution task.<n>We show that TDFlow attains 88.8% pass rate on SWE-Bench Lite.<n>We envision a human-LLM interactive system powered by TDFlow where human developers write tests.
  arXiv  Detail & Related papers  (2025-10-27T18:44:59Z)
• Program Synthesis via Test-Time Transduction [26.30808249424997]
  We introduce transductive program synthesis, a new formulation of the program synthesis task that explicitly leverages test inputs during synthesis.<n>We evaluate our approach on four benchmarks: Playgol, MBPP+, 1D-ARC, and programmatic world modeling on MiniGrid.<n>We demonstrate that our method significantly improves program synthesis in both accuracy and efficiency.
  arXiv  Detail & Related papers  (2025-09-22T06:53:32Z)
• SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner [53.54568352375669]
  We introduce **SWE-Flow**, a novel data synthesis framework grounded in Test-Driven Development (TDD)<n>Unlike existing software engineering data that rely on human-submitted issues, **SWE-Flow** automatically infers incremental development steps directly from unit tests.<n>We generated 16,061 training instances and 2,020 test instances from real-world GitHub projects, creating the **SWE-Flow-Eval** benchmark.
  arXiv  Detail & Related papers  (2025-06-10T17:23:33Z)
• Training Language Models to Generate Quality Code with Program Analysis Feedback [66.0854002147103]
  Code generation with large language models (LLMs) is increasingly adopted in production but fails to ensure code quality.<n>We propose REAL, a reinforcement learning framework that incentivizes LLMs to generate production-quality code.
  arXiv  Detail & Related papers  (2025-05-28T17:57:47Z)
• HLSTester: Efficient Testing of Behavioral Discrepancies with LLMs for High-Level Synthesis [4.544714097232974]
  Existing methods for testing behavioral discrepancies in high-level synthesis (HLS) are still immature. We propose HLSTester, a large language model (LLM) aided testing framework that efficiently detects behavioral discrepancies in HLS. To mitigate hallucinations in LLMs, the testbenches for original C/C++ programs are leveraged to guide LLMs in generating HLS-compatible testbenches.
  arXiv  Detail & Related papers  (2025-04-20T14:45:01Z)
• Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation [69.62857948698436]
  Recent advances in large language models (LLMs) have improved their performance on coding benchmarks. However, improvement is plateauing due to the exhaustion of readily available high-quality data. We propose Sol-Ver, a self-play solver-verifier framework that jointly improves a single model's code and test generation capacity.
  arXiv  Detail & Related papers  (2025-02-20T18:32:19Z)
• UnitCoder: Scalable Iterative Code Synthesis with Unit Test Guidance [65.01483640267885]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet code generation remains a major challenge. We introduce UnitCoder, a systematic pipeline leveraging model-generated unit tests to guide and validate the code generation process. Our work presents a scalable approach that leverages model-generated unit tests to guide the synthesis of high-quality code data from pre-training corpora.
  arXiv  Detail & Related papers  (2025-02-17T05:37:02Z)
• The Potential of LLMs in Automating Software Testing: From Generation to Reporting [0.0]
  Manual testing, while effective, can be time consuming and costly, leading to an increased demand for automated methods.<n>Recent advancements in Large Language Models (LLMs) have significantly influenced software engineering.<n>This paper explores an agent-oriented approach to automated software testing, using LLMs to reduce human intervention and enhance testing efficiency.
  arXiv  Detail & Related papers  (2024-12-31T02:06:46Z)
• AFlow: Automating Agentic Workflow Generation [36.61172223528231]
  Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains. We introduce AFlow, an automated framework that efficiently explores this space using Monte Carlo Tree Search. Empirical evaluations across six benchmark datasets demonstrate AFlow's efficacy, yielding a 5.7% average improvement over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-10-14T17:40:40Z)
• Benchmarking Agentic Workflow Generation [80.74757493266057]
  We introduce WorFBench, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures. We also present WorFEval, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms. We observe that the generated can enhance downstream tasks, enabling them to achieve superior performance with less time during inference.
  arXiv  Detail & Related papers  (2024-10-10T12:41:19Z)
• Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification [76.14641982122696]
  We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control. We show that our approach leads to an LLM that produces fewer inappropriate responses while achieving competitive performance on benchmarks and a toxicity detection task.
  arXiv  Detail & Related papers  (2024-10-07T23:38:58Z)
• AIME: AI System Optimization via Multiple LLM Evaluators [79.03422337674664]
  AIME is an evaluation protocol that utilizes multiple LLMs that each independently generate an evaluation on separate criteria and then combine them via concatenation. We show AIME outperforming baseline methods in code generation tasks, with up to $62%$ higher error detection rate and up to $16%$ higher success rate than a single LLM evaluation protocol on LeetCodeHard and HumanEval datasets.
  arXiv  Detail & Related papers  (2024-10-04T04:03:24Z)
• SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents [50.82665351100067]
  FlowGen is a code generation framework that emulates software process models based on multiple Large Language Model (LLM) agents. We evaluate FlowGenScrum on four benchmarks: HumanEval, HumanEval-ET, MBPP, and MBPP-ET.
  arXiv  Detail & Related papers  (2024-03-23T14:04:48Z)
• FlowMind: Automatic Workflow Generation with LLMs [12.848562107014093]
  This paper introduces a novel approach, FlowMind, leveraging the capabilities of Large Language Models (LLMs) We propose a generic prompt recipe for a lecture that helps ground LLM reasoning with reliable Application Programming Interfaces (APIs) We also introduce NCEN-QA, a new dataset in finance for benchmarking question-answering tasks from N-CEN reports on funds.
  arXiv  Detail & Related papers  (2024-03-17T00:36:37Z)
• Reinforcement Learning from Automatic Feedback for High-Quality Unit Test Generation [12.503002900186997]
  Large Language Models (LLMs) have gained popularity for code generation, including the automated creation of test cases.<n>LLMs are often trained on vast amounts of publicly available code, which may include test cases that do not adhere to best practices.<n>We propose a novel technique called Reinforcement Learning from Static Quality Metrics (RLSQM)
  arXiv  Detail & Related papers  (2023-10-03T18:48:31Z)
• CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning [92.36705236706678]
  "CodeRL" is a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning. During inference, we introduce a new generation procedure with a critical sampling strategy. For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives.
  arXiv  Detail & Related papers  (2022-07-05T02:42:15Z)
• Fault-Aware Neural Code Rankers [64.41888054066861]
  We propose fault-aware neural code rankers that can predict the correctness of a sampled program without executing it. Our fault-aware rankers can significantly increase the pass@1 accuracy of various code generation models.
  arXiv  Detail & Related papers  (2022-06-04T22:01:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.