Tencent Youtu Lab

Everything Fervor AI has published that touches Tencent Youtu Lab — 1 piece, newest first.

• ContextPilot Trains an Agent to Delete Its Own Context, and the Reward Never Asks What It Deleted

  ContextPilot's terminal reward is answer correctness plus format plus an invalid-call penalty, with no term for whether a given deletion was safe, so the model learns…