$\pi$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows

ArXi:2605.14678v1 Announce Type: new The rise of personal assistant agents, e.g., OpenClaw, highlights the growing potential of large language models to users across everyday life and work. A core challenge in these settings is proactive assistance, since users often begin with underspecified requests and leave important needs, constraints, or preferences unstated. However, existing benchmarks rarely evaluate whether agents can identify and act on such hidden intents before they are explicitly stated, especially in sustained multi-turn interactions where user needs emerge gradually.