通过工作流归纳的多轮智能体科学文献搜索

摘要

科学文献搜索往往不仅需要从单一查询中检索论文：用户的意图不明确、依赖于偏好，并通过交互不断演变。现有的搜索代理通常依赖固定流程或隐式纯语言推理，导致其搜索策略难以控制、检查和优化。我们提出PaperPilot，一个多轮文献搜索代理，将科学搜索构建为工作流归纳。给定一篇锚点论文和一个用户查询，PaperPilot构建一个由论文搜索算子组成的可执行有向无环图（DAG），包括关键词搜索、引文扩展、过滤、评分、重排序和证据提取。随后利用用户反馈来优化查询和工作流本身。我们通过监督工作流模仿和在受控工作流损坏上的偏好优化来训练PaperPilot。实验表明，在多轮交互下，PaperPilot-9B相比基础Qwen3.5-9B工具集代理有所提升，Hit@5从58.0提高到77.0，MRR从47.5提高到59.4，nDCG@10从26.8提高到32.5，同时工作流执行错误率从9.5%降至0%。这些结果表明，显式且可编辑的搜索工作流为将文献搜索代理与复杂的科学意图对齐提供了有效且可控的接口。

English

Scientific literature search often requires more than retrieving papers from a single query: users' intents are underspecified, preference-dependent, and evolve through interaction. Existing search agents typically rely on fixed pipelines or implicit language-only reasoning, making their search strategies difficult to control, inspect, and refine. We introduce PaperPilot, a multi-turn literature search agent that frames scientific search as workflow induction. Given an anchor paper and a user query, PaperPilot constructs an executable DAG of paper-search operators, including keyword search, citation expansion, filtering, scoring, reranking, and evidence extraction. User feedback is then used to refine both the query and the workflow itself. We train PaperPilot with supervised workflow imitation and preference optimization over controlled workflow corruptions. Experiments show that PaperPilot-9B improves over the base Qwen3.5-9B toolset agent under multi-turn interaction, increasing Hit@5 from 58.0 to 77.0, MRR from 47.5 to 59.4, and nDCG@10 from 26.8 to 32.5, while reducing workflow execution errors from 9.5% to 0%. These results show that explicit, editable search workflows provide an effective and controllable interface for aligning literature search agents with complex scientific intent.