25 papers
Rethinking SZZ Search Strategies: Lessons from Claude Code
Inase Kondo, Masanari Kondo, Daniel M. German +3
Identifying bug-inducing commits (BICs) is important for studying software bugs and maintaining software, yet the accuracy of existing SZZ methods remains limited. Although various…
PreMaQ: Predicting Maintainability-Related Quality of LLM-Generated Code Before Generation
Taiki Wakamatsu, Yuta Ishimoto, Masanari Kondo +1
As large language models (LLMs) become increasingly capable of code generation, adopting generated code in software development requires assessing not only its functional correctne…
Multi-SWT-Bench: A Multilingual Benchmark for Reproduction Test Generation
Kazuki Kusama, Sota Nakashima, Haruka Tokumasu +3
Reproduction test generation translates a natural-language issue description into executable tests that fail on the original code and pass after the issue is resolved, providing ex…
A Study on the Impact of Natural Language Differences in Prompts on Automatic Code Generation Using LLMs
Haruka Tokumasu, Masanari Kondo, Alexander Serebrenik +5
Large Language Models (LLMs) have demonstrated remarkable performance in automatic code generation tasks, thereby encouraging new research in this area. Although numerous studies h…
Exploring the Potential of Program Flowcharts on Code Generation Using Multimodal LLMs
Yuki Toi, Tao Xiao, Kazushi Tomoto +2
In recent years, Large Language Models (LLMs) have made significant strides, leading to the emergence of multimodal LLMs capable of processing diverse inputs such as images and aud…
ThinkLog: Leveraging Reasoning for Log Statement Generation
Kazuki Kusama, Honglin Shu, Masanari Kondo +2
Runtime logs are an important source of information that supports software maintenance. To obtain useful logs, developers spend significant effort identifying appropriate log locat…
How Well Do LLMs Generate Taxonomies in the SE Domain? A Multi-perspective Evaluation Framework
Sota Nakashima, Yuta Ishimoto, Masanari Kondo +2
Taxonomies provide a shared conceptual framework for organizing heterogeneous observations in software engineering (SE) research. Manually constructing such taxonomies is labor-int…
Directed Symbolic Execution for Vulnerability Discovery: An LLM-Guided Approach in KLEE
Lingfeng Chen, Tao Xiao, Masanari Kondo +1
Symbolic execution effectively discovers security violations but suffers from path explosion. Engines like KLEE therefore use path prioritization heuristics to order state explorat…
RepTran: Search-Based Repair of Transformer Models
Yuta Ishimoto, Paolo Arcaini, Fuyuki Ishikawa +3
To ensure the overall quality of AI-enabled software, not only traditional software components but also AI components need to be tested and repaired. Among AI components, Transform…
Large Language Models for Multi-Lingual Equivalent Mutant Detection: An Extended Empirical Study
Honglin Shu, Zhao Tian, Dong Wang +5
Mutation testing is a powerful technique for ensuring software quality. However, the presence of equivalent mutants introduces unnecessary costs and biases, limiting its practical…
Leveraging Language Models for Log Statement Generation in Multilingual Scenarios: How Far Are We?
Kazuki Kusama, Honglin Shu, Masanari Kondo +1
Log statements capture critical information for software maintenance activities such as testing, debugging, and failure analysis. Because of this importance, developers must carefu…
"Refactoring Runaway": Understanding and Mitigating Tangled Refactorings in Coding Agents for Issue Resolution
Zhao Tian, Zifan Zhang, Tao Xiao +4
Recent advances in coding agents have shown remarkable progress in software issue resolution. In practice, real-world issues are typically bug fixes or feature requests in which hu…
Toward Linking Declined Proposals and Source Code: An Exploratory Study on the Go Repository
Sota Nakashima, Masanari Kondo, Mahmoud Alfadel +4
Traceability links are key information sources for software developers, connecting software artifacts. Such links play an important role, particularly between contribution artifact…
Why Agentic-PRs Get Rejected: A Comparative Study of Coding Agents
Sota Nakashima, Yuta Ishimoto, Masanari Kondo +2
Agentic coding -- software development workflows in which autonomous coding agents plan, implement, and submit code changes with minimal human involvement -- is rapidly gaining tra…
Leveraging Mutation Analysis for LLM-based Repair of Quantum Programs
Chihiro Yoshida, Yuta Ishimoto, Olivier Nourry +4
In recent years, Automated Program Repair (APR) techniques specifically designed for quantum programs have been proposed. However, existing approaches often suffer from low repair…
AILINKPREVIEWER: Enhancing Code Reviews with LLM-Powered Link Previews
Panya Trakoolgerntong, Tao Xiao, Masanari Kondo +4
Code review is a key practice in software engineering, where developers evaluate code changes to ensure quality and maintainability. Links to issues and external resources are ofte…
Large-Scale Empirical Analysis of Continuous Fuzzing: Insights from 1 Million Fuzzing Sessions
Tatsuya Shirai, Olivier Nourry, Yutaro Kashiwa +3
Software vulnerabilities are constantly being reported and exploited in software products, causing significant impacts on society. In recent years, the main approach to vulnerabili…
How Small is Enough? Empirical Evidence of Quantized Small Language Models for Automated Program Repair
Kazuki Kusama, Honglin Shu, Masanari Kondo +1
Background: Large language models (LLMs) have greatly improved the accuracy of automated program repair (APR) methods. However, LLMs are constrained by high computational resource…
On the Evaluation of Large Language Models in Multilingual Vulnerability Repair
Dong wang, Junji Yu, Honglin Shu +4
Various Deep Learning-based approaches with pre-trained language models have been proposed for automatically repairing software vulnerabilities. However, these approaches are limit…
How Far Have LLMs Come Toward Automated SATD Taxonomy Construction?
Sota Nakashima, Yuta Ishimoto, Masanari Kondo +2
Technical debt refers to suboptimal code that degrades software quality. When developers intentionally introduce such debt, it is called self-admitted technical debt (SATD). Since…
Evaluating Large Language Models for Multilingual Vulnerability Detection at Dual Granularities
Honglin Shu, Michael Fu, Junji Yu +4
Various deep learning-based approaches utilizing pre-trained language models (PLMs) have been proposed for automated vulnerability detection. With recent advancements in large lang…
Evaluating Mutation-based Fault Localization for Quantum Programs
Yuta Ishimoto, Masanari Kondo, Naoyasu Ubayashi +4
Quantum computers leverage the principles of quantum mechanics to execute operations. They require quantum programs that define operations on quantum bits (qubits), the fundamental…
A Preliminary Study of Large Language Models for Multilingual Vulnerability Detection
Junji Yu, Honglin Shu, Michael Fu +4
Deep learning-based approaches, particularly those leveraging pre-trained language models (PLMs), have shown promise in automated software vulnerability detection. However, existin…
Myth: The loss of core developers is a critical issue for OSS communities
Olivier Nourry, Masanari Kondo, Shinobu Saito +3
Throughout their lifetime, open-source software systems will naturally attract new contributors and lose existing contributors. Not all OSS contributors are equal, however, as some…