FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Wei, Zhang, Xin, Guo, Zhongxin, Mao, Shaoguang, Luo, Wen, Peng, Guangyue, Huang, Yangyu, Wang, Houfeng, Li, Scarlett
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915350404136960
author Li, Wei
Zhang, Xin
Guo, Zhongxin
Mao, Shaoguang
Luo, Wen
Peng, Guangyue
Huang, Yangyu
Wang, Houfeng
Li, Scarlett
author_facet Li, Wei
Zhang, Xin
Guo, Zhongxin
Mao, Shaoguang
Luo, Wen
Peng, Guangyue
Huang, Yangyu
Wang, Houfeng
Li, Scarlett
contents Implementing new features in repository-level codebases is a crucial application of code generation models. However, current benchmarks lack a dedicated evaluation framework for this capability. To fill this gap, we introduce FEA-Bench, a benchmark designed to assess the ability of large language models (LLMs) to perform incremental development within code repositories. We collect pull requests from 83 GitHub repositories and use rule-based and intent-based filtering to construct task instances focused on new feature development. Each task instance containing code changes is paired with relevant unit test files to ensure that the solution can be verified. The feature implementation requires LLMs to simultaneously possess code completion capabilities for new components and code editing abilities for other relevant parts in the code repository, providing a more comprehensive evaluation method of LLMs' automated software engineering capabilities. Experimental results show that LLMs perform significantly worse in the FEA-Bench, highlighting considerable challenges in such repository-level incremental code development.
format Preprint
id arxiv_https___arxiv_org_abs_2503_06680
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation
Li, Wei
Zhang, Xin
Guo, Zhongxin
Mao, Shaoguang
Luo, Wen
Peng, Guangyue
Huang, Yangyu
Wang, Houfeng
Li, Scarlett
Software Engineering
Computation and Language
Implementing new features in repository-level codebases is a crucial application of code generation models. However, current benchmarks lack a dedicated evaluation framework for this capability. To fill this gap, we introduce FEA-Bench, a benchmark designed to assess the ability of large language models (LLMs) to perform incremental development within code repositories. We collect pull requests from 83 GitHub repositories and use rule-based and intent-based filtering to construct task instances focused on new feature development. Each task instance containing code changes is paired with relevant unit test files to ensure that the solution can be verified. The feature implementation requires LLMs to simultaneously possess code completion capabilities for new components and code editing abilities for other relevant parts in the code repository, providing a more comprehensive evaluation method of LLMs' automated software engineering capabilities. Experimental results show that LLMs perform significantly worse in the FEA-Bench, highlighting considerable challenges in such repository-level incremental code development.
title FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation
topic Software Engineering
Computation and Language
url https://arxiv.org/abs/2503.06680