AI助手该拒绝你时，它根本不知道
你让AI帮你订机票，它不会想到你上周刚跟伴侣吵完架、正打算给个惊喜。这篇论文点破一个被忽视的问题：助手只负责执行，不负责判断这个请求在你这儿合不合适。研究者造了个数据集，把请求和用户隐藏的个人事实(比如刚离婚、在戒酒)配对，发现现有模型几乎找不到这些关键信息——因为它们藏在知识库里，得靠多步推理才能挖出来。他们提出的PaceMaker用多个AI代理分工：一个改写问题、一个在知识图谱里跳着找、一个过滤冲突证据，效果明显更好。这不是你明天能用的功能，但它指向一个方向：未来的助手得学会说“不”，而且得知道为什么。
📄 原文摘要(英文)
Personalized assistants should not only comply with user requests but also assess whether those requests are appropriate given the user's current circumstances. However, prior work has primarily focused on accurately executing requests, overlooking the need for assistants to account for context and engage in conflict-based refusal. Furthermore, while existing work on conflict or safety detection relies on explicitly provided factors, real-world scenarios often involve implicit factors that must be retrieved from a knowledge base (KB). To this end, we introduce Personalized Assistants for Conflict Evaluation (PACE), a dataset for evaluating whether models can identify latent constraints, expressed as egocentric knowledge or events, that render seemingly reasonable user requests inappropriate. PACE pairs user requests grounded in well-defined personas with egocentric KB facts, requiring models to integrate contextual evidence to determine whether a request is conflicting. This implicit retrieval setting hinders the direct association between user requests and conflict-inducing knowledge, making it difficult for existing models to identify relevant user-specific facts. To address this challenge, we further propose PaceMaker, a multi-agent framework in which specialized agents coordinate across query reformulation, multi-hop graph traversal, and conflict-aware filtering to retrieve contextually decisive evidence. Experiments on PACE evaluate both evidence retrieval quality and conflict decision accuracy, showing that PaceMaker consistently outperforms existing approaches.