ATime-Consistent Benchmark for Repository-Level Software Engineering Evaluation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xianpeng, Sun, Sun, Haonan, Yu, Tian, Ma, Sheng, Zhang, Qincheng, Rao, Lifei, Tian, Chen
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911548000174080
author Xianpeng
Sun
Sun, Haonan
Yu, Tian
Ma, Sheng
Zhang, Qincheng
Rao, Lifei
Tian, Chen
author_facet Xianpeng
Sun
Sun, Haonan
Yu, Tian
Ma, Sheng
Zhang, Qincheng
Rao, Lifei
Tian, Chen
contents Evaluation of repository-aware software engineering systems is often confounded by synthetic task design, prompt leakage, and temporal contamination between repository knowledge and future code changes. We present a time-consistent benchmark methodology that snapshots a repository at time T0, constructs repository-derived code knowledge using only artifacts available before T0, and evaluates on engineering tasks derived from pull requests merged in the future interval (T0, T1]. Each historical pull request is transformed into a natural-language task through an LLM-assisted prompt-generation pipeline, and the benchmark is formalized as a matched A/B comparison in which the same software engineering agent is evaluated with and without repository-derived code knowledge while all other variables are held constant. We also report a baseline characterization study on two open-source repositories, DragonFly and React, using three Claude-family models and four prompt granularities. Across both repositories, file-level F1 increases monotonically from minimal to guided prompts, reaching 0.8081 on DragonFly and 0.8078 on React for the strongest tested model. These results show that prompt construction is a first-order benchmark variable. More broadly, the benchmark highlights that temporal consistency and prompt control are core validity requirements for repository-aware software engineering evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26137
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ATime-Consistent Benchmark for Repository-Level Software Engineering Evaluation
Xianpeng
Sun
Sun, Haonan
Yu, Tian
Ma, Sheng
Zhang, Qincheng
Rao, Lifei
Tian, Chen
Software Engineering
Artificial Intelligence
Evaluation of repository-aware software engineering systems is often confounded by synthetic task design, prompt leakage, and temporal contamination between repository knowledge and future code changes. We present a time-consistent benchmark methodology that snapshots a repository at time T0, constructs repository-derived code knowledge using only artifacts available before T0, and evaluates on engineering tasks derived from pull requests merged in the future interval (T0, T1]. Each historical pull request is transformed into a natural-language task through an LLM-assisted prompt-generation pipeline, and the benchmark is formalized as a matched A/B comparison in which the same software engineering agent is evaluated with and without repository-derived code knowledge while all other variables are held constant. We also report a baseline characterization study on two open-source repositories, DragonFly and React, using three Claude-family models and four prompt granularities. Across both repositories, file-level F1 increases monotonically from minimal to guided prompts, reaching 0.8081 on DragonFly and 0.8078 on React for the strongest tested model. These results show that prompt construction is a first-order benchmark variable. More broadly, the benchmark highlights that temporal consistency and prompt control are core validity requirements for repository-aware software engineering evaluation.
title ATime-Consistent Benchmark for Repository-Level Software Engineering Evaluation
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2603.26137