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

TL;DR

Proactive Agent Research Environment (Pare) is a framework that simulates realistic user interactions in digital environments to evaluate proactive assistants, addressing limitations of existing flat API models.

Contribution

It introduces Pare, a stateful user simulation framework, and Pare-Bench, a diverse task benchmark for testing proactive agent capabilities.

Findings

Pare enables active user simulation with stateful models.

Pare-Bench includes 143 diverse tasks across multiple app domains.

The framework facilitates realistic evaluation of proactive assistants.

Abstract

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.