AI RESEARCH
Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents
arXiv CS.CL
•
ArXi:2605.28108v1 Announce Type: new A long-lived LLM agent, such as OpenClaw, earns its value by acting on a user's preferences and constraints across sessions, not just the current request. Yet today's agents keep what a user volunteers but rarely ask for what stays unspoken, leaving a proactivity gap in long-lived LLM agents: an agent cannot act on a preference it never obtained. As users delegate of their affairs to agents, the impact of this gap grows.