# Apple 等机构提出 Proactive Agent Research Environment （Pare），将应用建模为有限状态机以评估主动式智能体

- 来源：Apple Machine Learning Research（RSS）
- 发布时间：2026-07-14 08:00
- AIHOT 分数：52
- AIHOT 链接：https://aihot.virxact.com/items/cmrkt4mhu00y5bi5qsjj9xev6
- 原文链接：https://machinelearning.apple.com/research/proactive-agent-research-environment

## AI 摘要

现有用户模拟框架将应用建模为扁平的工具调用 API，无法捕捉数字环境中用户交互的状态性和顺序性。Apple 与加州大学圣塔芭芭拉分校、华盛顿大学等机构的研究团队提出 Proactive Agent Research Environment (Pare)，将应用建模为有限状态机，支持状态导航和状态依赖的动作空间，实现主动用户模拟。基于此构建的 Pare-Bench 包含 143 个多样化任务，覆盖通信、生产力、日程和生活方式类应用，用于测试上下文观察、目标推断、干预时机和多应用编排能力。

## 正文

AuthorsDeepak Nathani†, Cheng Zhang‡, Chang Huan†, Jiaming Shan†, Yinfei Yang**, Alkesh Patel, Zhe Gan, William Yang Wang†, Michael Saxon§, Xin Eric Wang†

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.

† University of California, Santa Barbara

‡ Independent Researcher

§ University of Washington

** Work done while at Apple

Related readings and updates.

Reinforcement Learning for Long-Horizon Interactive LLM Agents

February 5, 2025research area Methods and Algorithms

Interactive digital agents (IDAs) leverage APIs of stateful digital environments to perform tasks in response to user requests. While IDAs powered by instruction-tuned large language models (LLMs) can react to feedback from interface invocations in multi-step exchanges, they have not been trained in their respective digital environments. Prior methods accomplish less than half of tasks in sophisticated benchmarks such as AppWorld. We present a…

Towards Learning Multi-Agent Negotiations via Self-Play

January 28, 2019research area Computer VisionWorkshop at ICCV

Making sophisticated, robust, and safe sequential decisions is at the heart of intelligent systems. This is especially critical for planning in complex multi-agent environments, where agents need to anticipate other agents’ intentions and possible future actions. Traditional methods formulate the problem as a Markov Decision Process, but the solutions often rely on various assumptions and become brittle when presented with corner cases. In…

Discover opportunities in Machine Learning.