Year: 2025
Type: preprint
Abstract: 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
Source: arXiv (Cornell University)
Authors: Shi, Xiaofeng, Li, Yuduo, Kou, Qian, Yu, Longbin, Xie, Jinxin, Zhou, Hua
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4417488777