138 citations · 181 across the 41 of their papers we have counts for
45 papers
Who Broke Me? Execution-Guided Repair of Behavioral Dependency Breaks
Juntao Chen, Tingting Bi, Yanlin Wang +1
Dependency upgrades can break downstream projects without changing the library interface. Such behavioral breaking changes are difficult for developers to fix, because the failing…
XAgent: eXecution-guided Agentic AI for Effective Localization and Resolution of GitHub Issues
Hieu Huynh, Patanamon Thongtanunam, Michael Fu +2
Agentic AI has enabled capabilities in leveraging Large Language Models (LLMs) to autonomously resolve repository-level GitHub issues. However, due to the reliance on limited stati…
AgenticRepair: Multi-Faceted Program Context Engineering for Agentic Vulnerability Repair
Michael Fu, Qiyue Mei, Patanamon Thongtanunam +1
Automated vulnerability repair aims to reduce the time and effort required to patch security flaws from a vulnerability triage report. Recent agentic AI approaches have shown promi…
Is Agentic Code Review Helpful? Mining Developers' Feedback to CodeRabbit Reviews in the Wild
Hong Yi Lin, Mingzhao Liang, Patanamon Thongtanunam +1
Agentic code review, where autonomous agents provide code review comments on pull requests, is increasingly integrated into development workflows, yet there is limited empirical ev…
Agentic Code Review in the Terminal: A Trajectory-Level Analysis of Behavior, Cost, and Human-Alignment
Wachiraphan Charoenwet, Kla Tantithamthavorn, Patanamon Thongtanunam +3
Agentic code review in terminal-based environments enables early feedback during local development before pull request creation. However, existing evaluations remain performance-ce…
Breaking Changes in Software Ecosystems: A Systematic Literature Review
Juntao Chen, Tingting Bi, Yanlin Wang +1
Modern software systems rely on dependency networks of reusable libraries, where breaking changes propagate and cause downstream consumers to fail. Despite growing research across…
AI-Assisted Code Review as a Scaffold for Code Quality and Self-Regulated Learning: An Experience Report
Eduardo Oliveira, Michael Fu, Patanamon Thongtanunam +2
Code review is central to software engineering education but hard to scale in capstone projects due to tight deadlines, uneven peer feedback, and limited prior experience. We inves…
When AI Models Become Dependencies: Studying the Evolution of Pre-Trained Model Reuse in Downstream Software Systems
Peerachai Banyongrakkul, Mansooreh Zahedi, Christoph Treude +2
Modern software systems have transitioned from purely code-based architectures to AI-integrated systems where pre-trained models (PTMs) serve as permanent dependencies. However, wh…
Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision
Hong Yi Lin, Chunhua Liu, Haoyu Gao +2
In today's AI-assisted software engineering landscape, developers increasingly depend on LLMs that are highly capable, yet inherently imperfect. The tendency of these models to pro…
AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection
Wachiraphan Charoenwet, Kla Tantithamthavorn, Patanamon Thongtanunam +3
Secure code review is critical during pre-integration, where Atlassian developers rely on lightweight analysis tools, while deep security assessment is deferred to later stages, de…
HalluJudge: A Reference-Free Hallucination Detection for Context Misalignment in Code Review Automation
Kla Tantithamthavorn, Hong Yi Lin, Patanamon Thongtanunam +3
Large Language models (LLMs) have shown strong capabilities in code review automation, such as review comment generation, yet they suffer from hallucinations -- where the generated…
Issue-Oriented Agent-Based Framework for Automated Review Comment Generation
Shuochuan Li, Dong Wang, Patanamon Thongtanunam +3
Code review (CR) is a crucial practice for ensuring software quality. Various automated review comment generation techniques have been proposed to streamline the labor-intensive pr…
Enhancing Code Review through Fuzzing and Likely Invariants
Wachiraphan Charoenwet, Patanamon Thongtanunam, Van-Thuan Pham +1
Many software projects employ manual code review to gatekeep defects and vulnerabilities in the code before integration. However, reviewers often work under time pressure and rely…
Enhancing Neural Code Representation with Additional Context
Huy Nguyen, Christoph Treude, Patanamon Thongtanunam
Automated program comprehension underpins many software engineering tasks, from code summarisation to clone detection. Recent deep learning models achieve strong results but typica…
What Types of Code Review Comments Do Developers Most Frequently Resolve?
Saul Goldman, Hong Yi Lin, Jirat Pasuksmit +11
Large language model (LLM)-powered code review automation tools have been introduced to generate code review comments. However, not all generated comments will drive code changes.…
Exploring the Potential of Large Language Models in Fine-Grained Review Comment Classification
Linh Nguyen, Chunhua Liu, Hong Yi Lin +1
Code review is a crucial practice in software development. As code review nowadays is lightweight, various issues can be identified, and sometimes, they can be trivial. Research ha…
Hallucinations in Code Change to Natural Language Generation: Prevalence and Evaluation of Detection Metrics
Chunhua Liu, Hong Yi Lin, Patanamon Thongtanunam
Language models have shown strong capabilities across a wide range of tasks in software engineering, such as code generation, yet they suffer from hallucinations. While hallucinati…
From Release to Adoption: Challenges in Reusing Pre-trained AI Models for Downstream Developers
Peerachai Banyongrakkul, Mansooreh Zahedi, Patanamon Thongtanunam +2
Pre-trained models (PTMs) have gained widespread popularity and achieved remarkable success across various fields, driven by their groundbreaking performance and easy accessibility…
Human-In-The-Loop Software Development Agents: Challenges and Future Directions
Jirat Pasuksmit, Wannita Takerngsaksiri, Patanamon Thongtanunam +8
Multi-agent LLM-driven systems for software development are rapidly gaining traction, offering new opportunities to enhance productivity. At Atlassian, we deployed Human-in-the-Loo…
A Systematic Survey on Debugging Techniques for Machine Learning Systems
Thanh-Dat Nguyen, Haoye Tian, Bach Le +2
Debugging ML software (i.e., the detection, localization and fixing of faults) poses unique challenges compared to traditional software largely due to the probabilistic nature and…
CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models
Hong Yi Lin, Chunhua Liu, Haoyu Gao +2
State-of-the-art large language models (LLMs) have demonstrated impressive code generation capabilities but struggle with real-world software engineering tasks, such as revising so…
Should Code Models Learn Pedagogically? A Preliminary Evaluation of Curriculum Learning for Real-World Software Engineering Tasks
Kyi Shin Khant, Hong Yi Lin, Patanamon Thongtanunam
Learning-based techniques, especially advanced pre-trained models for code have demonstrated capabilities in code understanding and generation, solving diverse software engineering…
Too Noisy To Learn: Enhancing Data Quality for Code Review Comment Generation
Chunhua Liu, Hong Yi Lin, Patanamon Thongtanunam
Code review is an important practice in software development, yet it is time-consuming and requires substantial effort. While open-source datasets have been used to train neural mo…
Human-In-the-Loop Software Development Agents
Wannita Takerngsaksiri, Jirat Pasuksmit, Patanamon Thongtanunam +7
Recently, Large Language Models (LLMs)-based multi-agent paradigms for software engineering are introduced to automatically resolve software development tasks (e.g., from a given i…