AI agents that keep improving themselves
AREX-2 trains AI agents to reflect and self-improve across many rounds, without needing human feedback.
Go Deeper →
5 short cards · What problem it solves, How it works, What they found …
Also today
Read today's briefing →Get it every morning
Today's top five AI stories, one line each, at 7am Eastern. Free. One-click unsubscribe.