让论文检索系统自我进化，精准找文献还杜绝虚构引用。
Towards Recursive Self-Evolving Agentic Literature Retrieval
- 通过迭代分析意图与证据，动态优化检索结果。
- 在38个学科中F1分数是谷歌学术的16.5倍，成本仅1%。
- 适合科研人员高效查文献，尤其怕假引用的场景。
科学文献检索需理解复杂查询意图同时保证来源真实。传统关键词和嵌入式系统虽能返回真实文献但忽略深层意图，大语言模型虽可捕捉丰富意图却可能编造引用。我们提出PaSaMaster——一种递归自进化代理式文献检索系统，通过迭代分析意图、检索经验证的论文并基于证据计算相关性得分实现精准排序。该系统融合自进化检索机制，从排序证据中持续优化搜索意图；采用无幻觉排名，在已验证论文而非生成引用上评分；以及低成本规划-检索分离设计，将前沿大模型用于意图理解，而用轻量模型与定制语料库处理检索与打分。在涵盖38个学科的PaSaMaster-Bench测试中，PaSaMaster的F1分数较Google Scholar高出16.5倍，较GPT-5.2高37.8%，成本仅为1%，同时将源幻觉率从生成式大模型的32.66%降至零。
原文摘要 · Abstract (English)
Scientific literature retrieval must understand complex search intents while preserving source authenticity. Traditional keyword and embedding-based systems return authentic sources but miss nuanced intents, whereas large language models capture richer intents but may fabricate citations. We introduce PaSaMaster, a Recursive Self-Evolving agentic literature retrieval system that iteratively analyzes intent, retrieves verified papers and ranks them with evidence-grounded relevance scores. PaSaMaster combines self-evolving retrieval that refines search intent from ranked evidence over time, hallucination-free ranking over verified papers rather than generated citations, and cost-efficient planning--retrieval separation that reserves frontier LLMs for intent understanding while delegating retrieval and scoring to lightweight models and customized corpora. Across 38 disciplines in PaSaMaster-Bench, PaSaMaster achieves a 16.5$\times$ higher F1-score than Google Scholar and a 37.8\% higher F1-score than GPT-5.2 at about 1\% of the cost, while reducing source hallucination from 32.66\% in generative LLMs to zero: https://github.com/sjtu-sai-agents/PaSaMaster
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。