104 citations · 201 across the 20 of their papers we have counts for
18 papers · 1 filter
ExplainBench: Evaluating Code Explanations from Agents
Zhiyuan Pan, Sungmin Kang, Imam Nur Bani Yusuf +1
Large Language Model (LLM) agents have seen rapid adoption in software engineering. As agents take a greater role in the actual generation of code, they are making larger changes,…
Skills for the future software profession: beyond agentic AI!
Abhik Roychoudhury, Sungmin Kang, Baishakhi Ray
As coding agents are rapidly changing software engineering, a natural question is: what are the core skills needed by future software engineers? To identify where software engineer…
Finding the Needle in the Crash Stack: Industrial-Scale Crash Root Cause Localization with AutoCrashFL
Sungmin Kang, Sumi Yun, Jingun Hong +2
Fault Localization (FL) aims to identify root causes of program failures. FL typically targets failures observed from test executions, and as such, often involves dynamic analyses…
AutoCodeSherpa: Symbolic Explanations in AI Coding Agents
Sungmin Kang, Haifeng Ruan, Abhik Roychoudhury
Large language model (LLM) agents integrate external tools with one or more LLMs to accomplish specific tasks. Agents have rapidly been adopted by developers, and they are starting…
COSMosFL: Ensemble of Small Language Models for Fault Localisation
Hyunjoon Cho, Sungmin Kang, Gabin An +1
LLMs are rapidly being adopted to build powerful tools and agents for software engineering, but most of them rely heavily on extremely large closed-source models. This, in turn, ca…
Lachesis: Predicting LLM Inference Accuracy using Structural Properties of Reasoning Paths
Naryeong Kim, Sungmin Kang, Gabin An +1
Large Language Models are increasingly used to build agents to perform more complex tasks. As LLMs perform more complicated reasoning through longer interactions, self-consistency,…
Beyond pip install: Evaluating LLM Agents for the Automated Installation of Python Projects
Louis Milliken, Sungmin Kang, Shin Yoo
Many works have recently proposed the use of Large Language Model (LLM) based agents for performing `repository level' tasks, loosely defined as a set of tasks whose scopes are gre…
Identifying Inaccurate Descriptions in LLM-generated Code Comments via Test Execution
Sungmin Kang, Louis Milliken, Shin Yoo
Software comments are critical for human understanding of software, and as such many comment generation techniques have been proposed. However, we find that a systematic evaluation…
Evaluating Diverse Large Language Models for Automatic and General Bug Reproduction
Sungmin Kang, Juyeon Yoon, Nargiz Askarbekkyzy +1
Bug reproduction is a critical developer activity that is also challenging to automate, as bug reports are often in natural language and thus can be difficult to transform to test…
The GitHub Recent Bugs Dataset for Evaluating LLM-based Debugging Applications
Jae Yong Lee, Sungmin Kang, Juyeon Yoon +1
Large Language Models (LLMs) have demonstrated strong natural language processing and code synthesis capabilities, which has led to their rapid adoption in software engineering app…
A Quantitative and Qualitative Evaluation of LLM-Based Explainable Fault Localization
Sungmin Kang, Gabin An, Shin Yoo
Fault Localization (FL), in which a developer seeks to identify which part of the code is malfunctioning and needs to be fixed, is a recurring challenge in debugging. To reduce dev…
Towards Autonomous Testing Agents via Conversational Large Language Models
Robert Feldt, Sungmin Kang, Juyeon Yoon +1
Software testing is an important part of the development cycle, yet it requires specialized expertise and substantial developer effort to adequately test software. Recent discoveri…
Towards Objective-Tailored Genetic Improvement Through Large Language Models
Sungmin Kang, Shin Yoo
While Genetic Improvement (GI) is a useful paradigm to improve functional and nonfunctional aspects of software, existing techniques tended to use the same set of mutation operator…
Explainable Automated Debugging via Large Language Model-driven Scientific Debugging
Sungmin Kang, Bei Chen, Shin Yoo +1
Automated debugging techniques have the potential to reduce developer effort in debugging, and have matured enough to be adopted by industry. However, one critical issue with exist…
A Bayesian Framework for Automated Debugging
Sungmin Kang, Wonkeun Choi, Shin Yoo
Debugging takes up a significant portion of developer time. As a result, automated debugging techniques including Fault Localization (FL) and Automated Program Repair (APR) have ga…
Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproduction
Sungmin Kang, Juyeon Yoon, Shin Yoo
Many automated test generation techniques have been developed to aid developers with writing tests. To facilitate full automation, most existing techniques aim to either increase c…
GLAD: Neural Predicate Synthesis to Repair Omission Faults
Sungmin Kang, Shin Yoo
Existing template and learning-based APR tools have successfully found patches for many benchmark faults. However, our analysis of existing results shows that omission faults pose…
SINVAD: Search-based Image Space Navigation for DNN Image Classifier Test Input Generation
Sungmin Kang, Robert Feldt, Shin Yoo
The testing of Deep Neural Networks (DNNs) has become increasingly important as DNNs are widely adopted by safety critical systems. While many test adequacy criteria have been sugg…