Is Three the Magic Number? An Empirical Evaluation of LLM-Based Repair Loops

• URL: http://arxiv.org/abs/2607.05197v1
• Date: Mon, 06 Jul 2026 15:14:10 GMT
• Title: Is Three the Magic Number? An Empirical Evaluation of LLM-Based Repair Loops
• Abstract summary: Iterative repair loops have become a core design pattern in LLM-based software engineering systems.<n>We study repair-loop effectiveness across multiple software engineering tasks, including code generation, test generation, and code translation.<n>We observe a consistent pattern of diminishing returns: the first three to four repair iterations account for most achievable gains, while later iterations contribute only marginal improvements.
• Score: 1.6093668627931699
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Iterative repair loops have become a core design pattern in LLM-based software engineering systems. These workflows repeatedly generate, validate, and repair artifacts using feedback such as compiler errors or test failures. Despite their widespread use, the impact of repair-loop iteration limits remains poorly understood, as most prior work adopts fixed, often arbitrary, repair budgets. We study repair-loop effectiveness across multiple software engineering tasks, including code generation, test generation, and code translation. Across several representative workflows, datasets, and contemporary low-cost LLMs, we observe a consistent pattern of diminishing returns: the first three to four repair iterations account for most achievable gains, while later iterations contribute only marginal improvements. We further find that repair behavior is influenced more strongly by workflow orchestration and feedback design than by the underlying model itself. These results suggest that repair budgets should be treated as an explicit experimental variable, as they directly affect evaluation outcomes, computational cost, runtime, and reproducibility in LLM-based software engineering research.

Related papers

• Unlocking LLM Code Correction with Iterative Feedback Loops [5.504955093712013]
  This study introduces metrics to evaluate code failures, analyze rectification patterns, and compare the effectiveness of reasoning and non-reasoning models.<n>Results show that reasoning models consistently improve over iterations, substantially outperforming non-reasoning models in leveraging feedback.
  arXiv  Detail & Related papers  (2026-06-16T04:47:42Z)
• QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization [50.722636027998]
  Large Language Models (LLMs) achieve strong program repair performance but often suffer from over-editing.<n>We propose PRepair, a framework that mitigates over-editing and improves repair accuracy.
  arXiv  Detail & Related papers  (2026-04-07T14:56:38Z)
• From Human to Machine Refactoring: Assessing GPT-4's Impact on Python Class Quality and Readability [46.83143241367452]
  Refactoring aims to improve code quality without altering program behavior.<n>Recent advances in Large Language Models (LLMs) have introduced new opportunities for automated code preservation.<n>We present an empirical study on LLM-driven classes using GPT-4o, applied to 100 Python classes from the ClassEval benchmark.<n>Our findings show that GPT-4o generally produces behavior-preservings that reduce code smells and improve quality metrics, albeit at the cost of decreased readability.
  arXiv  Detail & Related papers  (2026-01-19T15:22:37Z)
• Summary-Mediated Repair: Can LLMs use code summarisation as a tool for program repair? [0.0]
  Large Language Models (LLMs) often produce code with subtle implementation-level bugs despite strong benchmark performance.<n>We propose summary-mediated repair, a prompt-only pipeline for program repair.
  arXiv  Detail & Related papers  (2025-11-24T05:33:38Z)
• RelRepair: Enhancing Automated Program Repair by Retrieving Relevant Code [11.74568238259256]
  RelRepair retrieves relevant project-specific code to enhance automated program repair.<n>We evaluate RelRepair on two widely studied datasets, Defects4J V1.2 and ManySStuBs4J.
  arXiv  Detail & Related papers  (2025-09-20T14:07:28Z)
• Do AI models help produce verified bug fixes? [62.985237003585674]
  Large Language Models are used to produce corrections to software bugs.<n>This paper investigates how programmers use Large Language Models to complement their own skills.<n>The results are a first step towards a proper role for AI and LLMs in providing guaranteed-correct fixes to program bugs.
  arXiv  Detail & Related papers  (2025-07-21T17:30:16Z)
• The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models [48.073219761367184]
  We investigate an APR pipeline that balances the generation of multiple outputs and multiple rounds of iteration.<n>We fine-tune each model on an APR dataset with three sizes (1K, 30K, 65K) and two techniques (Full Fine-Tuning and LoRA)<n>Our results show that by using only a fraction (1%) of the fine-tuning dataset, we can achieve improvements of up to 78% in the number of plausible patches generated.
  arXiv  Detail & Related papers  (2025-05-05T18:06:51Z)
• FeedbackEval: A Benchmark for Evaluating Large Language Models in Feedback-Driven Code Repair Tasks [28.849481030601666]
  We introduce FeedbackEval, a benchmark for evaluating large language models' feedback comprehension and performance.<n>We conduct a comprehensive empirical study on five state-of-the-art LLMs, including GPT-4o, Claude-3.5, Gemini-1.5, GLM-4, and Qwen2.5.<n>Our results show that structured feedback, particularly in the form of test feedback, leads to the highest repair success rates, while unstructured feedback proves significantly less effective.
  arXiv  Detail & Related papers  (2025-04-09T14:43:08Z)
• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
  Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
  arXiv  Detail & Related papers  (2024-10-05T05:21:48Z)
• RePair: Automated Program Repair with Process-based Feedback [28.017321930042694]
  We show how small-scale language models (LM) can achieve excellent performance through process supervision and feedback. We develop a reward model that serves as a critic, providing feedback for the fine-tuned LM's action. The results show that process-based not only outperforms larger outcome-based generation methods, but also nearly matches the performance of closed-source commercial large-scale LMs.
  arXiv  Detail & Related papers  (2024-08-21T02:53:23Z)
• Investigating the Transferability of Code Repair for Low-Resource Programming Languages [57.62712191540067]
  Large language models (LLMs) have shown remarkable performance on code generation tasks. Recent works augment the code repair process by integrating modern techniques such as chain-of-thought reasoning or distillation. We investigate the benefits of distilling code repair for both high and low resource languages.
  arXiv  Detail & Related papers  (2024-06-21T05:05:39Z)
• MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning [25.03477973238162]
  Fine-tuning approaches for Large language models (LLMs) on program repair tasks overlook the need to reason about the logic behind code changes.<n>We apply MOobjective to fine-tune four open-source LLMs with different sizes and architectures.<n>We show that our fine-tuning strategy yields superior performance compared to the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-04-19T05:36:21Z)
• Is Self-Repair a Silver Bullet for Code Generation? [68.02601393906083]
  Large language models have shown remarkable aptitude in code generation, but still struggle to perform complex tasks. Self-repair -- in which the model debugs and repairs its own code -- has recently become a popular way to boost performance. We analyze Code Llama, GPT-3.5 and GPT-4's ability to perform self-repair on problems taken from HumanEval and APPS.
  arXiv  Detail & Related papers  (2023-06-16T15:13:17Z)

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.