AI 主动追问，不是话多，是问对
我们总嫌 AI 只会答不会问；这篇发现，会问的 AI 反而更少打扰你。研究者把「主动」拆成两种：顺着当前话题追问没说的细节(横向)，和根据早先线索挖出你没提的需求(纵向)。他们训练了一个「提问者」，专挑那些能带出更多关键信息的问题来问，不靠奖励模型打分，只靠问题答完能补回多少证据来选。在三个多跳问答基准上，同样预算下，它比同款模型直接提示更会问，在两个数据集上还赢过 15 倍大的模型；放进客服和零售场景，它用更少的问题完成更多任务，顾客也不用反复补充。它不是你明天就能装进产品的，但方向很实在：AI 的主动，不该是抢着说话，而是知道该问什么、何时闭嘴。
📄 原文摘要(英文)
An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested. Work on proactive agents mainly studies whether and when an agent should act on its own, not what information it should pursue. We study a distinct axis of proactivity: its content. Horizontal proactivity pursues unstated information that the current context already identifies, and vertical proactivity pursues needs that only earlier evidence reveals. A need graph, recovered from a benchmark's own decomposition, records which needs depend on which, so both forms, and whether the agent stops at the right time, can be scored from a transcript without a model judge. To learn this behavior, we propose Q&D (questioner and drafter), which trains a questioner to prefer the question whose continuation retrieves more of the required evidence, with no reward model or judge. On held-out splits of three multi-hop question-answering benchmarks, at equal retrieval spend, the trained questioner improves both forms of proactivity over the same model, prompted, and outperforms a prompted model 15times larger in the same role on two of the three, and the gain persists after controlling for question volume and length. Without further training, we place the questioner in an interactive customer-service agent with a simulated customer, where it completes more tasks while asking fewer questions, and in retail it outperforms the 15times larger model with fewer follow-up turns from the customer. These results show that proactivity depends not only on whether an agent acts without being asked, but also on what it chooses to pursue and when it stops.