让论文搜索像编程一样可编辑，用户能一步步优化找文献的流程。
Multi-Turn Agentic Scientific Literature Search via Workflow Induction
- 把找文献变成可执行的流程图，每步都可修改
- 多轮交互后准确率提升，错误率降为0%
- 适合需要精细调整搜索策略的研究者
科学文献搜索常需多轮交互：用户意图模糊、偏好变化且逐步明确。现有搜索代理依赖固定流程或隐式语言推理，难以控制与调试。我们提出PaperPilot，一种多轮文献搜索代理，将科学搜索建模为工作流归纳。给定锚论文和用户查询，PaperPilot构建可执行的有向无环图（DAG），包含关键词搜索、引文扩展、过滤、打分、重排序和证据提取等操作。用户反馈用于同时优化查询与工作流。通过监督式工作流模仿和偏好优化训练，对抗可控的流程破坏。实验表明，PaperPilot-9B在多轮交互下优于基线Qwen3.5-9B工具集代理，命中率（Hit@5）从58.0升至77.0，MRR从47.5升至59.4，nDCG@10从26.8升至32.5，工作流执行错误率从9.5%降至0%。结果证明，显式可编辑的搜索工作流为对齐复杂科研意图提供了高效可控的接口。
原文摘要 · Abstract (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.
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。