搜论文像搭积木：可编辑的工作流让AI更听话
现在的AI搜论文，你问一句它答一句，策略藏在黑箱里，错了你也改不了。这篇把搜索变成搭积木：AI先根据你的问题和一篇参考论文，自动生成一个搜索工作流——比如先关键词搜、再扩引用、再过滤、再打分——每一步都是看得见的模块。你可以在中间插一句“这个方向不对”，它不光改查询，还能直接改工作流本身。结果：9B小模型在多次交互后，命中率从58%跳到77%，工作流执行错误从9.5%降到0%。它不是你明天能用上的，但指明了方向：让AI的思考过程可编辑，比让它自己瞎猜靠谱得多。
📄 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.