6 papers
Provably Lossless Acceleration of DNN Mutation Testing via Memoization
Ali Ghanbari, Ben Greenman, Sasan Tavakkol +1
Mutation analysis has recently reemerged in the context of deep neural networks (DNNs) as a promising, but notoriously costly, approach for assessing test dataset adequacy. Existin…
From Discussion to Execution: Replicating Buggy and Correct Data Science Code
Ragib Shahariar Ayon, Mohammad Wardat, Shibbir Ahmed
Reproducing reliable data science code from informal sources is challenging due to ambiguous problem specifications, missing dependencies, and performance bottlenecks. Although dev…
ReqGenX: An Empirical Study of Atomic Decomposition, Artifact Regeneration, and Reconstruction for Legacy SRS Documents
Ragib Shahariar Ayon, Rayed Fahmi, Sumon Biswas +1
Background: Evaluating automated Software Requirements Specification (SRS) generation is challenging because few datasets provide fine-grained traceability between source requireme…
When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling
Niful Islam, Ragib Shahriar Ayon, Deepak George Thomas +2
Large Language Models (LLMs) have revolutionized intelligent application development. While standalone LLMs cannot perform any actions, LLM agents address the limitation by integra…
SpecPylot: Python Specification Generation using Large Language Models
Ragib Shahariar Ayon, Shibbir Ahmed
Automatically generating formal specifications could reduce the effort needed to improve program correctness, but in practice, this is still challenging. Many developers avoid writ…
AutoReSpec: A Framework for Generating Specification using Large Language Models
Ragib Shahariar Ayon, Shibbir Ahmed
Formal specification generation has recently drawn attention in software engineering as a way to improve program correctness without requiring manual annotations. Large Language Mo…