论文搜索新玩法：AI帮你画流程图找文献
你搜论文时是不是经常搜完一搜发现方向不对，得重新来？这篇研究把搜索过程变成了一个可编辑的流程图。你给一篇起点论文和需求，AI自动生成一个搜索工作流：先关键词搜、再引用扩展、然后过滤、打分、排序、提取证据——每一步都画成节点，你随时可以改。用户反馈后，AI还能自动调整整个流程。实验显示，这种显式工作流让搜索命中率从58%提升到77%，错误率从9.5%降到0%。它不是你明天就能用的工具，但提示了一个方向：未来AI搜索不再是黑箱，而是你可以看、可以改的流程图。
📄 原文摘要(英文)
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.