6 papers
SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
Jingzhi Gong, Ruizhen Gu, Zhiwei Fei +7
Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet current practice treats them as static, hand-crafted assets, or evolved on pa…
SafeTune: Search-based Harmfulness Minimisation for Large Language Models
Giordano d'Aloisio, David Williams, Giusy Annunziata +3
The widespread adoption of Large Language Models (LLMs) raises concerns about the potential harmfulness of their responses. In this paper, we first investigate the harmfulness of r…
Echo: Graph-Enhanced Retrieval and Execution Feedback for Issue Reproduction Test Generation
Zhiwei Fei, Yue Pan, Federica Sarro +4
Identifying the root cause of a bug remains difficult for many developers because bug reports often lack a bug reproducing test case that reliably triggers the failure. Manually wr…
Environment-in-the-Loop: Rethinking Code Migration with LLM-based Agents
Xiang Li, Zhiwei Fei, Ying Ma +3
Modern software systems continuously undergo code upgrades to enhance functionality, security, and performance, and Large Language Models (LLMs) have demonstrated remarkable capabi…
JMigBench: A Benchmark for Evaluating LLMs on Source Code Migration (Java 8 to Java 11)
Nishil Amin, Zhiwei Fei, Xiang Li +2
We build a benchmark to evaluate large language models (LLMs) for source code migration tasks, specifically upgrading functions from Java 8 to Java 11. We first collected a dataset…
Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories
Oorja Majgaonkar, Zhiwei Fei, Xiang Li +2
The increasing deployment of Large Language Model (LLM) agents for complex software engineering tasks has created a need to understand their problem-solving behaviours beyond simpl…