常驻Agent综述：130+页系统梳理状态管理

Great overview of always-on agents.

(bookmark it)

It's a new 130+ pages survey on always-on agents.

Simply put it, always-on agents are systems whose future behavior depends on durable state built up across earlier interactions. It treats that state as more than memory. Task ledgers, permissions, credentials, commitments, provenance, triggers, and externally committed effects all count.

The survey scores each state item on six axes, authority, scope, mutability, provenance, recoverability, and actionability, across a lifecycle that runs from write and retrieve through forget, audit, and rollback.

Paper: https://arxiv.org/abs/2606.30306

Learn to build effective AI agents in our academy: https://academy.dair.ai/