5 papers
EnvPilot: Systematic Design and Evaluation of an Experience-Augmented Agent for Software Environment Setup
Hanwu Chen, Hanyu Lin, Zhanjiang Yang +6
Environment Setup is a critical yet complex task in software engineering that relies heavily on expert knowledge. Existing automated environment setup methods lack the ability to a…
Heterogeneous Multi-Agent Modeling for Measurement and Network Analysis of the Data Service Market
Deyu Zhou, Yuwei Guo, Xudong Lu +3
With the increasing complexity of collaboration among various social entities and user demands, the factors affecting the stable development of the data service market are also gro…
PaperRepro: Automated Computational Reproducibility Assessment for Social Science Papers
Linhao Zhang, Tong Xia, Jinghua Piao +2
Computational reproducibility is essential for the credibility of scientific findings, particularly in the social sciences, where findings often inform real-world decisions. Manual…
Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving
Daoguang Zan, Zhirong Huang, Wei Liu +16
The task of issue resolving is to modify a codebase to generate a patch that addresses a given issue. However, existing benchmarks, such as SWE-bench, focus almost exclusively on P…
CodeV: Issue Resolving with Visual Data
Linhao Zhang, Daoguang Zan, Quanshun Yang +10
Large Language Models (LLMs) have advanced rapidly in recent years, with their applications in software engineering expanding to more complex repository-level tasks. GitHub issue r…