9 papers · 1 filter
Documentation Drift in AI-Generated Pull Requests
Will De Michele, Kla Tantithamthavorn
AI coding agents now contribute to software repositories at scale, yet their documentation practices remain uncharacterised. We analyse 29,669 AI-generated pull requests from 2,585…
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…
Requirements-Augmented Generation for Trustworthy Acceptance Testing of LLM-Based Software
Fanyu Wang, Chetan Arora, Zhenping Xie +4
LLM-based software (LBS) integrates large language models as core components to deliver flexible, personalised responses. Unlike traditional software with deterministic outputs, LB…
Towards a Risk Assessment of Malicious Skill Files in Coding Agents
Rui Yang, Michael Fu, Kla Tantithamthavorn +2
Autonomous coding agents are increasingly embedded in enterprise software workflows with delegated authority over connected systems. Central to this architecture is the agent skill…
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…
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…
CodeChat-Eval: Evaluating Large Language Models in Multi-Turn Code Refinement Dialogues
Guoxiang Guo, Kla Tantithamthavorn, Neelofar Neelofar +2
Large Language Models (LLMs) are increasingly used in software engineering to generate and refine code. In practice, developers often continue from an initial code generation reque…
RovoDev Code Reviewer: A Large-Scale Online Evaluation of LLM-based Code Review Automation at Atlassian
Kla Tantithamthavorn, Yaotian Zou, Andy Wong +8
Large Language Models (LLMs)-powered code review automation has the potential to transform code review workflows. Despite the advances of LLM-powered code review comment generation…
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…