Long-Term Memory

Memory sounds like a simple product feature. A user tells an assistant something today. The assistant remembers it tomorrow. Everyone applauds, the demo works, and someone writes “personalization” on a roadmap slide. Lovely. We have rediscovered a notebook. The harder problem begins when the user does not explicitly say what matters. A student says, “It’s fine.” A customer writes, “No worries.” A therapy-like support user replies with a short, polite sentence that looks neutral in isolation. Locally, the words are harmless. Historically, they may be resignation, guardedness, disappointment, or the emotional equivalent of quietly closing the door. ...

A task list is usually where enterprise automation becomes reassuringly boring. Someone defines the work. The system executes it. A dashboard turns green, or, in more honest organisations, amber with an explanation. The point is not mystery. The point is control. The paper behind this article, LLM Agents Beyond Utility: An Open-Ended Perspective, asks what happens when that tidy arrangement is disturbed: what if the agent does not merely complete tasks, but proposes them? What if it can remember what it has done, inspect its environment, write notes to itself, and continue across runs?1 ...