7 papers
COMMITGUARD: Differential Slice Fuzzing for Commit-Induced Bug Detection
Aniruddhan Murali, Noble Saji Mathews, Mahmoud Alfadel +1
Modern software systems evolve through frequent commits that implement bug fixes, features, and security patches. Although code review and testing are widely used to check these ch…
What Makes a Good Bug Report for an AI Agent?
Lara Khatib, Noble Saji Mathews, Meiyappan Nagappan +2
Automated program repair (APR) agents are transitioning from research benchmarks to developer workflows, yet they still begin with bug reports written for human developers. While d…
AssertFlip: Reproducing Bugs via Inversion of LLM-Generated Passing Tests
Lara Khatib, Noble Saji Mathews, Meiyappan Nagappan
Bug reproduction is critical in the software debugging and repair process, yet the majority of bugs in open-source and industrial settings lack executable tests to reproduce them a…
Does SWE-Bench-Verified Test Agent Ability or Model Memory?
Thanosan Prathifkumar, Noble Saji Mathews, Meiyappan Nagappan
SWE-Bench-Verified, a dataset comprising 500 issues, serves as a de facto benchmark for evaluating various large language models (LLMs) on their ability to resolve GitHub issues. B…
Is Your Automated Software Engineer Trustworthy?
Noble Saji Mathews, Meiyappan Nagappan
Large Language Models (LLMs) are being increasingly used in software engineering tasks, with an increased focus on bug report resolution over the past year. However, most proposed…
Design choices made by LLM-based test generators prevent them from finding bugs
Noble Saji Mathews, Meiyappan Nagappan
There is an increasing amount of research and commercial tools for automated test case generation using Large Language Models (LLMs). This paper critically examines whether recent…