SPAR: Scholar Paper Retrieval with LLM-based Agents for Enhanced Academic Search
This addresses the need for more flexible and effective scholarly search systems, though it appears incremental in improving retrieval methods.
The paper tackles the problem of academic literature retrieval by introducing SPAR, a multi-agent framework with RefChain-based query decomposition and query evolution, which achieves up to +56% F1 on AutoScholar and +23% F1 on SPARBench over baselines.
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