Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2507.15822

Do AI models help produce verified bug fixes?

Li Huang·Ilgiz Mustafin·Marco Piccioni·Alessandro Schena·Reto Weber·Bertrand Meyer
View original source ↗Read source document ↗Export metadata ↓

Abstract

Among areas of software engineering where AI techniques -- particularly, Large Language Models -- seem poised to yield dramatic improvements, an attractive candidate is Automatic Program Repair (APR), the production of satisfactory corrections to software bugs. Does this expectation materialize in practice? How do we find out, making sure that proposed corrections actually work? If programmers have access to LLMs, how do they actually use them to complement their own skills? To answer these questions, we took advantage of the availability of a program-proving environment, which formally determines the correctness of proposed fixes, to conduct a study of program debugging with two randomly assigned groups of programmers, one with access to LLMs and the other without, both validating their answers through the proof tools. The methodology relied on a division into general research questions (Goals in the Goal-Query-Metric approach), specific elements admitting specific answers (Queries), and measurements supporting these answers (Metrics). While applied so far to a limited sample size, the results are a first step towards delineating a proper role for AI and LLMs in providing guaranteed-correct fixes to program bugs. These results caused surprise as compared to what one might expect from the use of AI for debugging and APR. The contributions also include: a detailed methodology for experiments in the use of LLMs for debugging, which other projects can reuse; a fine-grain analysis of programmer behavior, made possible by the use of full-session recording; a definition of patterns of use of LLMs, with 7 distinct categories; and validated advice for getting the best of LLMs for debugging and Automatic Program Repair.

Explore related subjects

cs.SEcs.AI

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Li Huang, Ilgiz Mustafin, Marco Piccioni, Alessandro Schena, Reto Weber, Bertrand Meyer. 2025-08-04. Do AI models help produce verified bug fixes?. https://arxiv.org/abs/2507.15822

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

XScientist: A Git-Like Research Protocol for Long-Running Autonomous Scientific Discovery

Autonomous research systems can generate plausible papers while losing the decisions, failed branches, and evidence needed to inspect or continue the work. We present XScientist, a local-first, git-like protocol that treats research state, rather than a manuscript, as the unit of continuation. Hypotheses, experiment attempts, observations, claims, reviews, and handoffs are represented as typed, content-addressed objects in an exploration graph. Immutable checkpoints, explicit negative outcomes, claim-evidence closure, replay boundaries, and authority-aware gates make each transition inspectable without treating a passing integrity check as scientific truth. The protocol exports a portable Agent-Native Research Artifact (ARA) that another agent or human can inspect, fork, verify, and extend. A reference implementation integrates planning, execution, review, repair, and supervised long-running operation while preserving provenance across these stages. We evaluate the protocol with controlled artifact-integrity workloads and matched external task pilots, keeping native task performance separate from evidence and audit claims. The result is an interoperability and accountability layer for long-running autonomous science, with explicit boundaries where human judgment and independent evaluation remain necessary.

cs.SE↗
arXiv2026

AutoSQL: Extracting SQL Templates from Imperative ORM Code in Large-Scale Repositories

Suboptimal SQL queries can significantly degrade the performance of cloud systems, motivating the extraction and auditing of SQL statements before deployment. However, Go ORM frameworks construct SQL imperatively through scattered method-call sequences, making it difficult to statically recover the resulting SQL templates. We present AutoSQL, a system that reconstructs SQL templates from Go ORM code. AutoSQL constructs a Code Index, a directed graph that captures structural dependencies between functions, types, and global variables as navigable edges. It then traces upstream call chains from ORM invocation sites to identify database-interacting functions as entry points. For each entry point, an LLM agent traverses the Code Index to collect code slices that influence SQL generation, switching to pattern-based search when the graph cannot resolve a retrieval goal. We call this strategy Hybrid Context Retrieval. Once sufficient context is collected, the agent synthesizes SQL templates. Evaluation on a benchmark of 579 test-covered entry points and 1,186 runtime-traced SQL statements from five large-scale Go repositories shows that AutoSQL achieves 68.04% to 72.18% recall, exceeding the static reachability baseline by 11.80% to 15.94% and outperforming existing methods by 8.52% to 21.50%.

cs.SE↗
arXiv2026

The Vocabulary of Flaky Tests in Swift

Flaky tests produce non-deterministic outcomes without code change, eroding CI confidence and delaying deliveries. While vocabulary-based machine learning prediction has proven effective for Java and JavaScript, no study has evaluated it for Swift, a language whose testing style is dominated by UI and asynchronous code. We collect 91 flaky and 22,349 stable tests from 15 open-source Swift projects via re-execution and commit-history mining, then train five classifiers (Random Forest, Decision Tree, Naive Bayes, SVM, KNN) on TF-IDF unigram+bigram features under stratified 5-fold cross-validation. Random Forest achieves the best performance (Precision = 0.92, F1 = 0.86, AUC = 0.95) and substantially outperforms trivial baselines, among them a vocabulary-threshold rule applied to the most informative tokens, confirming a genuine discriminative signal (MCC = 0.75 vs. 0.08 for the best baseline). Information-gain analysis reveals two complementary signal types. Flakiness markers appear predominantly in unstable tests and comprise concurrency primitives (async, await), expectation-based synchronisation (expectation, fulfill), error propagation (throws), and explicit timing dependence (timeout, wait, now). Stability markers, chiefly the assertion vocabulary of plainly synchronous tests (xctassertequal), count as evidence against flakiness. Error analysis shows that the model fails when flakiness is hidden in shared infrastructure outside the test body or when async constructs are used in a deterministic context, exposing the intrinsic limit of lexical prediction. These results extend vocabulary-based flakiness detection to the Swift ecosystem and characterise both its effectiveness and its boundaries.

cs.SE↗