Saved in:
Bibliographic Details
Main Authors: Han, Junxiao, Wang, Yarong, Gu, Xiaodong, Gao, Cuiyun, Wan, Yao, Han, Song, Lo, David, Deng, Shuiguang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.09791
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908487846461440
author Han, Junxiao
Wang, Yarong
Gu, Xiaodong
Gao, Cuiyun
Wan, Yao
Han, Song
Lo, David
Deng, Shuiguang
author_facet Han, Junxiao
Wang, Yarong
Gu, Xiaodong
Gao, Cuiyun
Wan, Yao
Han, Song
Lo, David
Deng, Shuiguang
contents In this paper, we propose LibRec, a novel framework that integrates the capabilities of LLMs with retrieval-augmented generation(RAG) techniques to automate the recommendation of alternative libraries. The framework further employs in-context learning to extract migration intents from commit messages to enhance the accuracy of its recommendations. To evaluate the effectiveness of LibRec, we introduce LibEval, a benchmark designed to assess the performance in the library migration recommendation task. LibEval comprises 2,888 migration records associated with 2,368 libraries extracted from 2,324 Python repositories. Each migration record captures source-target library pairs, along with their corresponding migration intents and intent types. Based on LibEval, we evaluated the effectiveness of ten popular LLMs within our framework, conducted an ablation study to examine the contributions of key components within our framework, explored the impact of various prompt strategies on the framework's performance, assessed its effectiveness across various intent types, and performed detailed failure case analyses.
format Preprint
id arxiv_https___arxiv_org_abs_2508_09791
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LibRec: Benchmarking Retrieval-Augmented LLMs for Library Migration Recommendations
Han, Junxiao
Wang, Yarong
Gu, Xiaodong
Gao, Cuiyun
Wan, Yao
Han, Song
Lo, David
Deng, Shuiguang
Software Engineering
Artificial Intelligence
In this paper, we propose LibRec, a novel framework that integrates the capabilities of LLMs with retrieval-augmented generation(RAG) techniques to automate the recommendation of alternative libraries. The framework further employs in-context learning to extract migration intents from commit messages to enhance the accuracy of its recommendations. To evaluate the effectiveness of LibRec, we introduce LibEval, a benchmark designed to assess the performance in the library migration recommendation task. LibEval comprises 2,888 migration records associated with 2,368 libraries extracted from 2,324 Python repositories. Each migration record captures source-target library pairs, along with their corresponding migration intents and intent types. Based on LibEval, we evaluated the effectiveness of ten popular LLMs within our framework, conducted an ablation study to examine the contributions of key components within our framework, explored the impact of various prompt strategies on the framework's performance, assessed its effectiveness across various intent types, and performed detailed failure case analyses.
title LibRec: Benchmarking Retrieval-Augmented LLMs for Library Migration Recommendations
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2508.09791