预见与学习:在主动智能体中释放空闲时间计算
Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents
AI总结:
提出ProAct主动智能体架构,利用空闲时间计算预测并满足用户未来需求,通过ProActEval基准测试验证其在任务加速、减少用户努力和降低幻觉率方面的显著优势。
摘要:
虽然AI智能体在推理和工具使用方面展现出显著能力,但它们本质上仍然是被动的:仅在用户明确提示后才计算响应。这种范式忽略了一个关键机会:交互之间的空闲时间很大程度上被浪费,使得智能体无法为未来的用户需求做准备。为弥补这一差距,我们引入了ProAct,一种主动智能体架构,利用空闲时间计算来预测并满足可能即将出现的用户需求。通过分析不断演变的对话历史以及持久记忆,ProAct预测即将到来的需求并迭代获取信息,使智能体能够在用户发起查询之前解决知识差距并准备证据。为严格评估主动能力,我们还引入了ProActEval,一个包含40个领域200个场景的综合基准,具有可预测的需求链和多样化的用户认知特征。实验结果表明,与被动基线相比具有显著优势。ProAct通过减少14.8%的必要交互轮次加速任务完成,减少11.7%的用户努力,并在ProActEval上将幻觉率降低28.1%。此外,MemBench评估证实ProAct达到了最先进的反思准确性,突显其持续且稳健的性能。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。