12 papers
Beyond FLOPs: Energy-Aware Knowledge Distillation for Sustainable LLMs on Code-Related Task
Enrique Barba Roque, Luís Cruz, Annibale Panichella
Background: Large Language Models (LLMs) are increasingly being applied to Software Engineering (SE) tasks, achieving high accuracy across problems such as clone detection, vulnera…
Test Case Selection for Deep Neural Networks: A Replication Study on LLMs for Code
Ali Asgari, Mitchell Olsthoorn, Annibale Panichella
Recently, test case selection (TCS) techniques have been explored to support the operational evaluation of deep neural networks (DNNs) under limited testing budgets, where labeling…
A Metamorphic Testing Approach to Diagnosing Memorization in LLM-Based Program Repair
Milan De Koning, Ali Asgari, Pouria Derakhshanfar +1
LLM-based automated program repair (APR) techniques have shown promising results in reducing debugging costs. However, prior results can be affected by data leakage: large language…
Real-World Fault Detection for C-Extended Python Projects with Automated Unit Test Generation
Lucas Berg, Lukas Krodinger, Stephan Lukasczyk +4
Many popular Python libraries use C-extensions for performance-critical operations allowing users to combine the best of the two worlds: The simplicity and versatility of Python an…
What Challenges Do Developers Face in AI Agent Systems? An Empirical Study on Stack Overflow & GitHub Issues
Ali Asgari, Annibale Panichella, Pouria Derakhshanfar +1
AI Agents have rapidly gained prominence in both research and industry as systems that extend large language models with planning, tool use, memory, and goal-directed action. Despi…
The Pursuit of Diversity: Multi-Objective Testing of Deep Reinforcement Learning Agents
Antony Bartlett, Cynthia Liem, Annibale Panichella
Testing deep reinforcement learning (DRL) agents in safety-critical domains requires discovering diverse failure scenarios. Existing tools such as INDAGO rely on single-objective o…