5 papers
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…
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…
SelfHeal: Empirical Fix Pattern Analysis and Bug Repair in LLM Agents
Niful Islam, Muhammad Anas Raza, Mohammad Wardat
Large Language Models (LLMs) have transformed software development and AI applications. While LLMs are designed for text processing, LLM agents extend this capability by enabling a…
Mock Deep Testing: Toward Separate Development of Data and Models for Deep Learning
Ruchira Manke, Mohammad Wardat, Foutse Khomh +1
While deep learning (DL) has permeated, and become an integral component of many critical software systems, today software engineering research hasn't explored how to separately te…
Leveraging Data Characteristics for Bug Localization in Deep Learning Programs
Ruchira Manke, Mohammad Wardat, Foutse Khomh +1
Deep Learning (DL) is a class of machine learning algorithms that are used in a wide variety of applications. Like any software system, DL programs can have bugs. To support bug lo…