Reproduce “LibRec: Benchmarking Retrieval-Augmented LLMs for Library Migration Recommendations” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Junxiao Han, Yarong Wang, Xiaodong Gu, Cuiyun Gao, Yao Wan, Song Han, David Lo, Shuiguang Deng
LibRec combines a developer’s stated reason for replacing a library with retrieved examples of similar historical swaps to rank candidate replacements. It uses an LLM to infer migration intent, retrieves three examples, and returns ten recommendations. On a 578-record Python benchmark, Claude-3.7-Sonnet achieves 0.792 Precision@10; this measures recovery of the annotated historical target, not project suitability or migration success.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.