Proactive agents must decide not only what to say but also whether and when to intervene. Many current systems rely on brittle heuristics or indiscriminate long reasoning, which offers little control over the benefit-burden tradeoff. We formulate the problem as cost-sensitive selective intervention and present PRISM, a novel framework that couples a decision-theoretic gate with a dual-process reasoning architecture. At inference time, the agent intervenes only when a calibrated probability of user acceptance exceeds a threshold derived from asymmetric costs of missed help and false alarms. Inspired by festina lente (Latin: "make haste slowly"), we gate by an acceptance-calibrated, cost-derived threshold and invoke a resource-intensive Slow mode with counterfactual checks only near the decision boundary, concentrating computation on ambiguous and high-stakes cases. Training uses gate-aligned, schema-locked distillation: a teacher running the full PRISM pipeline provides dense, executable supervision on unlabeled interaction traces, while the student learns a response policy that is explicitly decoupled from the intervention gate to enable tunable and auditable control. On ProactiveBench, PRISM reduces false alarms by 22.78% and improves F1 by 20.14% over strong baselines. These results show that principled decision-theoretic gating, paired with selective slow reasoning and aligned distillation, yields proactive agents that are precise, computationally efficient, and controllable. To facilitate reproducibility, we release our code, models, and resources at https://prism-festinalente.github.io/; all experiments use the open-source ProactiveBench benchmark.

翻译：主动智能体不仅需要决定说什么，还需要决定是否以及何时进行干预。当前的许多系统依赖于脆弱的启发式规则或不分场合的长链推理，这难以有效权衡干预的收益与负担。我们将该问题形式化为成本敏感的选择性干预，并提出 PRISM 这一新颖框架，该框架将决策论门控与双过程推理架构相结合。在推理阶段，只有当经过校准的用户接受概率超过一个由错失帮助与误报的不对称成本推导出的阈值时，智能体才会进行干预。受 Festina Lente（拉丁语："欲速则不达"）启发，我们采用一个基于接受概率校准和成本推导的阈值进行门控，并仅在接近决策边界时调用一个包含反事实检查的资源密集型"慢速"模式，从而将计算资源集中于模糊且高风险的情况。训练采用门控对齐、模式锁定的知识蒸馏方法：运行完整 PRISM 流程的教师模型在未标注的交互轨迹上提供密集、可执行的监督信号，而学生模型则学习一个明确与干预门控解耦的响应策略，以实现可调节且可审计的控制。在 ProactiveBench 基准测试中，PRISM 相较于强基线模型，将误报率降低了 22.78%，并将 F1 分数提升了 20.14%。这些结果表明，基于原则的决策论门控，结合选择性的慢速推理与对齐的蒸馏，能够产生精确、计算高效且可控的主动智能体。为促进可复现性，我们在 https://prism-festinalente.github.io/ 发布了代码、模型及相关资源；所有实验均使用开源的 ProactiveBench 基准。