arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.00842cs.AIcs.LGcs.MA
收藏

主动代理研究环境:模拟活跃用户以评估主动助手

Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants

University of California, Santa Barbara(加州大学圣塔芭芭拉分校);Apple, USA(苹果公司(美国));University of Washington(华盛顿大学);Independent Researcher, USA(独立研究员(美国))

Deepak Nathani, Cheng Zhang, Chang Huan, Jiaming Shan, Yinfei Yang, Alkesh Patel, Zhe Gan, William Yang Wang, Michael Saxon, Xin Eric Wang

AI总结:

本文提出Pare框架,通过状态机模拟用户交互,构建并评估主动代理,同时引入Pare-Bench基准测试143种不同任务,测试上下文感知、目标推理和多应用协调能力。

摘要:

主动代理能够预测用户需求并自主执行任务,具有成为数字助手的巨大潜力,但缺乏真实的用户模拟框架阻碍了其发展。现有方法将应用建模为扁平的工具调用API,未能捕捉数字环境中用户交互的状态性和顺序性,使得真实用户模拟不可行。我们引入主动代理研究环境(Pare),一种用于构建和评估数字环境中主动代理的框架。Pare将应用建模为有限状态机,具有状态ful导航和状态依赖的动作空间,使活跃用户模拟成为可能。在此基础上,我们提出了Pare-Bench,一个包含143种不同任务的基准测试,涵盖通信、生产力、调度和生活方式应用,旨在测试上下文感知、目标推理、干预时机和多应用协调能力。

英文摘要:

Proactive agents that anticipate user needs and autonomously execute tasks hold great promise as digital assistants, yet the lack of realistic user simulation frameworks hinders their development. Existing approaches model apps as flat tool-calling APIs, failing to capture the stateful and sequential nature of user interaction in digital environments and making realistic user simulation infeasible. We introduce Proactive Agent Research Environment (Pare), a framework for building and evaluating proactive agents in digital environments. Pare models applications as finite state machines with stateful navigation and state-dependent action space for the user simulator, enabling active user simulation. Building on this foundation, we present Pare-Bench, a benchmark of 143 diverse tasks spanning communication, productivity, scheduling, and lifestyle apps, designed to test context observation, goal inference, intervention timing, and multi-app orchestration.

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。

↑