SPAR：基于LLM智能体的学术论文检索系统，助力高效学术搜索

摘要

近期，大型语言模型（LLMs）的进展为学术文献检索开辟了新的机遇。然而，现有系统往往依赖固定的处理流程，且推理能力有限。我们提出了SPAR，一个多智能体框架，它通过基于RefChain的查询分解与查询演化，实现了更为灵活高效的搜索。为了支持系统化评估，我们还构建了SPARBench，这是一个包含专家标注相关性标签的挑战性基准。实验结果显示，SPAR显著超越了现有强基线，在AutoScholar上F1分数提升高达+56%，在SPARBench上相比表现最佳的基线也有+23%的提升。SPAR与SPARBench共同为推进学术检索研究提供了一个可扩展、可解释且高性能的基础。代码与数据将在以下网址提供：https://github.com/xiaofengShi/SPAR。

English

Recent advances in large language models (LLMs) have opened new opportunities for academic literature retrieval. However, existing systems often rely on rigid pipelines and exhibit limited reasoning capabilities. We introduce SPAR, a multi-agent framework that incorporates RefChain-based query decomposition and query evolution to enable more flexible and effective search. To facilitate systematic evaluation, we also construct SPARBench, a challenging benchmark with expert-annotated relevance labels. Experimental results demonstrate that SPAR substantially outperforms strong baselines, achieving up to +56% F1 on AutoScholar and +23% F1 on SPARBench over the best-performing baseline. Together, SPAR and SPARBench provide a scalable, interpretable, and high-performing foundation for advancing research in scholarly retrieval. Code and data will be available at: https://github.com/xiaofengShi/SPAR

SPAR：基于LLM智能体的学术论文检索系统，助力高效学术搜索

SPAR: Scholar Paper Retrieval with LLM-based Agents for Enhanced Academic Search

摘要

Support