Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914437315690496 |
|---|---|
| author | Nathani, Deepak Zhang, Cheng Huan, Chang Shan, Jiaming Yang, Yinfei Patel, Alkesh Gan, Zhe Wang, William Yang Saxon, Michael Wang, Xin Eric |
| author_facet | Nathani, Deepak Zhang, Cheng Huan, Chang Shan, Jiaming Yang, Yinfei Patel, Alkesh Gan, Zhe Wang, William Yang Saxon, Michael Wang, Xin Eric |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00842 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants Nathani, Deepak Zhang, Cheng Huan, Chang Shan, Jiaming Yang, Yinfei Patel, Alkesh Gan, Zhe Wang, William Yang Saxon, Michael Wang, Xin Eric Artificial Intelligence Machine Learning Multiagent Systems 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. |
| title | Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants |
| topic | Artificial Intelligence Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2604.00842 |