5 citations · 6 across the 11 of their papers we have counts for
12 papers · 1 filter
Developer Experiences with Cursor AI-native IDE
Haoran Xue, Gias Uddin, Song Wang
AI-powered integrated development environments (IDEs) are increasingly positioned as practical tools for software development, integrating AI assistance into everyday activities su…
Impossible to hide secret ...: Uncovering Security and Privacy Issues in LLM-native IDEs
Mostafijur Rahman Akhond, Md Afif Al Mamun, Gias Uddin +1
LLM-native IDEs (Integrated Development Environments), aka LIDEs, are designed from the ground up to work with Large Language Models (LLMs). LIDEs have found remarkable success in…
Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation
Sanjeepan Sivapiran, Gias Uddin
Large Language Model (LLM) alignment trains an LLM using preference data to produce outputs that better meet established quality standards. While LLM alignment techniques are studi…
BLAgent: Agentic RAG for File-Level Bug Localization
Md Afif Al Mamun, Gias Uddin
Bug localization remains a key bottleneck for large language model (LLM)-based software maintenance, where accurately identifying faulty code is essential for debugging, root cause…
ABTest: Behavior-Driven Testing for AI Coding Agents
Wuyang Dai, Moses Openja, Hung Viet Pham +3
AI coding agents are increasingly integrated into real-world software development workflows, yet their robustness under diverse and adversarial scenarios remains poorly understood.…
Engineering Pitfalls in AI Coding Tools: An Empirical Study of Bugs in Claude Code, Codex, and Gemini CLI
Ruixin Zhang, Wuyang Dai, Hung Viet Pham +3
The rapid integration of Large Language Models (LLMs) into software development workflows has given rise to a new class of AI-assisted coding tools, such as Claude-Code, Codex, and…
Stack Trace-Based Crash Deduplication with Transformer Adaptation
Md Afif Al Mamun, Gias Uddin, Lan Xia +1
Automated crash reporting systems generate large volumes of duplicate reports, overwhelming issue-tracking systems and increasing developer workload. Traditional stack trace-based…
TriagerX: Dual Transformers for Bug Triaging Tasks with Content and Interaction Based Rankings
Md Afif Al Mamun, Gias Uddin, Lan Xia +1
Pretrained Language Models or PLMs are transformer-based architectures that can be used in bug triaging tasks. PLMs can better capture token semantics than traditional Machine Lear…
PAGENT: Learning to Patch Software Engineering Agents
Haoran Xue, Gias Uddin, Song Wang
LLM Agents produce patches automatically to resolve an issue. However, they can generate inaccurate patches. Little is known about the root causes behind those failed patches or ho…
ChatGPT Inaccuracy Mitigation during Technical Report Understanding: Are We There Yet?
Salma Begum Tamanna, Gias Uddin, Song Wang +2
Hallucinations, the tendency to produce irrelevant/incorrect responses, are prevalent concerns in generative AI-based tools like ChatGPT. Although hallucinations in ChatGPT are stu…
SWE-Bench+: Enhanced Coding Benchmark for LLMs
Reem Aleithan, Haoran Xue, Mohammad Mahdi Mohajer +3
Large Language Models (LLMs) in Software Engineering (SE) can offer assistance for coding. To facilitate a rigorous evaluation of LLMs in practical coding contexts, Carlos et al. i…
Checker Bug Detection and Repair in Deep Learning Libraries
Nima Shiri Harzevili, Mohammad Mahdi Mohajer, Jiho Shin +8
Checker bugs in Deep Learning (DL) libraries are critical yet not well-explored. These bugs are often concealed in the input validation and error-checking code of DL libraries and…