Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents

2026-05-25

AI Summary

This work addresses the limitation of conventional AI agents, which respond only upon explicit user prompts and fail to anticipate needs during interaction gaps. To overcome this, we propose ProAct, a novel architecture that systematically leverages idle computational resources to proactively predict user intentions and pre-fetch relevant information during inactive periods, utilizing dialogue state tracking, long-term memory, and iterative retrieval. We introduce ProActEval, the first benchmark tailored for evaluating proactive reasoning, along with a model of cognitive diversity. Experimental results demonstrate that ProAct reduces interaction turns by 14.8%, decreases user burden by 11.7%, and lowers hallucination rates by 28.1% on ProActEval, while achieving state-of-the-art performance in reflection accuracy on MemBench.

Abstract

While AI agents demonstrate remarkable capabilities in reasoning and tool use, they remain fundamentally reactive: they compute responses only after explicit user prompts. This paradigm ignores a critical opportunity: the idle time between interactions is largely wasted, leaving agents unable to prepare for future user needs. To bridge this gap, we introduce ProAct, a proactive agent architecture that leverages idle-time compute to anticipate and fulfill likely upcoming user needs. By analyzing evolving dialogue history together with persistent memory, ProAct predicts upcoming needs and iteratively acquires information, allowing the agent to resolve knowledge gaps and prepare evidence before the user initiates a query.To rigorously evaluate proactive capabilities, we also introduce ProActEval, a comprehensive benchmark comprising 200 scenarios across 40 domains, featuring predictable need chains and diverse user cognitive profiles. Empirical results demonstrate significant advantages over reactive baselines. ProAct accelerates task completion by reducing required turns by 14.8%, decreases user effort by 11.7%, and cuts hallucination rates by 28.1% on ProActEval. Furthermore, MemBench evaluations confirm that ProAct achieves state-of-the-art reflective accuracy, underscoring its sustained and robust performance.

Problem

• proactive agents
• idle-time compute
• anticipatory reasoning
• user needs prediction
• reactive paradigm

Innovation

• proactive agents
• idle-time compute
• anticipatory reasoning
• persistent memory
• ProActEval