用智能代理提升学术论文检索，让搜索更灵活精准
SPAR: Scholar Paper Retrieval with LLM-based Agents for Enhanced Academic Search
- 采用多智能体架构，通过分解和演化查询增强搜索能力
- 在两个基准上分别提升56%和23%的F1值，显著优于基线
- 适合需要高效精准查找文献的研究者与工具开发者
大型语言模型（LLMs）的发展为学术文献检索带来了新机遇。然而，现有系统多依赖僵化流程，推理能力有限。本文提出SPAR，一种基于多智能体的框架，结合RefChain式的查询分解与查询演化，实现更灵活高效的检索。为支持系统评估，我们构建了SPARBench——一个具有专家标注相关性标签的挑战性基准。实验表明，SPAR显著超越强基线，在AutoScholar上最高提升56% F1，SPARBench上提升23%。SPAR与SPARBench共同提供了一个可扩展、可解释且高性能的学术检索基础。代码与数据将公开于：https://github.com/xiaofengShi/SPAR
原文摘要 · Abstract (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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。