Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency

• URL: http://arxiv.org/abs/2608.14065v2
• Date: Mon, 17 Aug 2026 01:36:36 GMT
• Title: Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency
• Abstract summary: This study focuses on how repair performance is shaped by bug complexity, fault localization, reasoning settings, and costs.<n>Although structurally complex bugs and imprecise fault localization make repair more challenging, LLM-based APR techniques still achieve competitive repair effectiveness.
• Score: 1.9703625025720701
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Background: Software bugs remain a critical challenge in development, necessitating effective Automated Program Repair (APR) techniques. While Large Language Model (LLM)-based APR systems have shown promise, prior studies primarily focus on overall repair effectiveness. The effects of bug complexity, fault localization, reasoning settings, and repair cost-effectiveness remain insufficiently explored. Aims: This study presents a comprehensive empirical analysis of LLM-based APR, focusing on how repair performance is shaped by bug complexity, fault localization, reasoning settings, and costs. Method: We evaluate two APR techniques (ChatRepair and CodeCorrector) using three LLMs (DeepSeek, GPT, and Llama), and examine their performance across diverse levels of bug complexity and localization strategies through a multi-dimensional empirical framework and statistical analysis. Results: Although structurally complex bugs and imprecise fault localization make repair more challenging, LLM-based APR techniques still achieve competitive repair effectiveness. Imprecise fault localization can substantially enlarge the performance gap between APR techniques. Furthermore, higher-cost LLMs and stronger reasoning settings do not consistently yield better cost-efficiency, revealing a nontrivial trade-off between repair effectiveness and computational cost. Conclusions: Over 50% of moderately complex bugs can be repaired by low-cost LLM-based APR techniques. The repair effectiveness gap between APR techniques becomes larger as fault localization becomes less precise. GPT-5 repairs 7 and 39 more complex bugs than DeepSeek-V4-pro and DeepSeek-V3.2, respectively; whereas the total repair cost of DeepSeek-V3.2 shows the best cost-efficiency performance.

Related papers

• FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization [61.43300970020897]
  Large language models (LLMs) are increasingly used for optimization modeling and solver-code generation.<n>Existing benchmarks are limited to small or simplified examples far below real-world scale and complexity.<n>We introduce FrontierOR, among the first benchmarks to evaluate LLM-based efficient algorithm design for realistic large-scale optimization problems.
  arXiv  Detail & Related papers  (2026-05-24T20:10:42Z)
• Optimized Deferral for Imbalanced Settings [52.48138985215643]
  Learning algorithms can be significantly improved by routing complex or uncertain inputs to specialized experts.<n>This approach, known as learning to defer, is essential in domains like natural language generation, medical diagnosis, and computer vision.<n>We present a comprehensive study of two-stage learning to defer in expert imbalance settings.
  arXiv  Detail & Related papers  (2026-04-30T11:15:37Z)
• Self-Correction Distillation for Structured Data Question Answering [50.98882432829651]
  Small-scale language models (LLMs) are prone to errors in generating structured queries.<n>We propose a self-correction distillation (SCD) method to improve the structured data QA ability of small-scale LLMs.
  arXiv  Detail & Related papers  (2025-11-11T09:01:51Z)
• Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs [57.10533368622962]
  Self-correction of large language models (LLMs) emerges as a critical component for enhancing their reasoning performance.<n>This study introduces CorrectBench, a benchmark developed to evaluate the effectiveness of self-correction strategies.<n>Our findings reveal that: 1) Self-correction methods can improve accuracy, especially for complex reasoning tasks; 2) Mixing different self-correction strategies yields further improvements, though it reduces efficiency; and 3) Reasoning LLMs (e.g., DeepSeek-R1) have limited optimization under additional self-correction methods and have high time costs.
  arXiv  Detail & Related papers  (2025-10-17T02:40:19Z)
• BloomAPR: A Bloom's Taxonomy-based Framework for Assessing the Capabilities of LLM-Powered APR Solutions [19.682278660857584]
  We introduce BloomAPR, a novel dynamic evaluation framework grounded in Bloom's taxonomy.<n>Our framework offers a structured approach to assess the cognitive capabilities of LLM-powered APR solutions across progressively complex reasoning levels.<n>Our findings show that while these solutions exhibit basic reasoning skills, their performance increases with synthetically generated bugs.
  arXiv  Detail & Related papers  (2025-09-29T20:16:11Z)
• Specification-Guided Repair of Arithmetic Errors in Dafny Programs using LLMs [79.74676890436174]
  We present an APR tool for Dafny that uses formal specifications as oracles for fault localization and repair.<n>We localize faults through a series of steps, which include using Hoare logic to determine the state of each statement within the program.<n>Our tool achieves 89.6% fault localization coverage and GPT-4o mini yields the highest repair success rate of 74.18%.
  arXiv  Detail & Related papers  (2025-07-04T15:36:12Z)
• APRMCTS: Improving LLM-based Automated Program Repair with Iterative Tree Search [5.535308342351274]
  APRMCTS incorporates Monte Carlo Tree Search (MCTS) into patch searching by performing a global evaluation of the explored patches and selecting the most promising one for subsequent refinement and generation.<n>Our experiments on 835 bugs from Defects4J demonstrate that, when integrated with GPT-3.5, APRMCTS can fix a total of 201 bugs, which outperforms all state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-07-02T15:44:12Z)
• ORMind: A Cognitive-Inspired End-to-End Reasoning Framework for Operations Research [56.961539386979354]
  We introduce ORMind, a cognitive-inspired framework that enhances optimization through counterfactual reasoning.<n>Our approach emulates human cognition, implementing an end-to-end workflow that transforms requirements into mathematical models and executable code.<n>It is currently being tested internally in Lenovo's AI Assistant, with plans to enhance optimization capabilities for both business and consumer customers.
  arXiv  Detail & Related papers  (2025-06-02T05:11:21Z)
• 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)
• Hybrid Automated Program Repair by Combining Large Language Models and Program Analysis [12.7034916462208]
  Automated Program Repair (APR) has garnered significant attention due to its potential to streamline the bug repair process for human developers. This paper introduces an innovative APR approach called GIANTREPAIR. Based on this insight, GIANTREPAIR first constructs patch skeletons from LLM-generated patches to confine the patch space, and then generates high-quality patches tailored to specific programs.
  arXiv  Detail & Related papers  (2024-06-03T05:05:12Z)
• How Far Can We Go with Practical Function-Level Program Repair? [11.71750828464698]
  This paper investigates the effect of few-shot learning mechanism and the auxiliary repair-relevant information on function-level APR. We propose an LLM-based function-level APR technique, namely SRepair, which adopts a dual-LLM framework to leverage the power of the auxiliary repair-relevant information.
  arXiv  Detail & Related papers  (2024-04-19T12:14:09Z)
• The Right Prompts for the Job: Repair Code-Review Defects with Large Language Model [15.885824575879763]
  Automatic program repair (APR) techniques have the potential to reduce manual efforts in uncovering and repairing program defects during the code review (CR) process. However, the limited accuracy and considerable time costs associated with existing APR approaches hinder their adoption in industrial practice. Recent advancements in Large Language Models (LLMs) have enhanced their ability to comprehend natural and programming languages, enabling them to generate patches based on review comments.
  arXiv  Detail & Related papers  (2023-12-29T06:12:15Z)

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.