PRISM: Festina Lente Proactivity -- Risk-Sensitive, Uncertainty-Aware Deliberation for

On ProactiveBench, PRISM reduces false alarms by 22.78% and improves F1 by 20.14% over strong baselines. It comes from a paper posted to arXiv on 30 October 2026. 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. 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.

Why it counts

On ProactiveBench, PRISM reduces false alarms by 22.78% and improves F1 by 20.14% over strong baselines. To facilitate reproducibility, we release our code, models, and resources at https://prism-festinalente.github.io/; all experiments use the open-source ProactiveBench benchmark.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.