TIDE：通過模板導向迭代的主動多重問題發現

摘要

智能体被广泛部署为文档、工具和代码的辅助助手。然而，它们通常仅对用户的显式请求做出响应，而这些请求只反映了用户已注意到的问题，而许多其他重要问题却共存于更广泛的用户上下文中，在显而易见的表象下隐藏着，且其总数事先未知。我们将此定义为从上下文中发现多个隐藏问题的任务，即需要揭示共存的问题、为其提供支持性证据，并配以具体的行动方案。为此，我们提出了TIDE——一种模板引导的迭代框架，包含两种互补机制。具体而言，基于"单次预测往往聚焦于最显著的案例并产生泛化论断"这一观察，我们提出了迭代发现机制，该机制每轮输出一小批候选结果，同时以已发现内容为条件，从而后续轮次扩展覆盖范围；此外，我们还提出了思想模板，即从先前已解决的案例中提炼出的可复用模式，这些模式指明了应关注哪些上下文信号以及如何将它们关联起来，从而将每次预测锚定到可识别的问题类别。我们在两个现实场景——个人工作空间和软件仓库——中使用四种模型主干验证了TIDE，结果表明，在任务覆盖、识别和解决方面，该方法相较于单次预测和并行多智能体基线均有显著提升。

English

Agents are widely deployed as assistants over documents, tools, and code. However, they typically act only on explicit user requests, which surface only the problems the user has noticed, while many other important problems coexist, hidden in plain sight, within the broader user context, with their total number unknown in advance. We frame this as the task of discovering multiple hidden problems from context, in which coexisting problems should be uncovered, grounded in supporting evidence, and paired with concrete actions. To this end, we introduce TIDE, a template-guided iterative framework with two complementary mechanisms. Specifically, motivated by the observation that single-pass prediction anchors on the most salient cases and yields generic claims, we propose iterative discovery, which surfaces a small batch of candidates per round while conditioning on what has already been found, so subsequent rounds extend coverage; and thought templates, reusable schemas distilled from previously solved cases that specify what contextual signals to attend to and how to connect them, anchoring each prediction in a recognizable problem class. We validate TIDE on two realistic settings, personal workspaces and software repositories, across four model backbones, showing substantial gains over single-shot and parallel multi-agent baselines on task coverage, identification, and resolution.