First AutoHarness, then AutoContext, now AutoCompact. I am seeing a rising trend of work that trains models to natively support more of what the harness does. ...

First AutoHarness, then AutoContext, now AutoCompact.

I am seeing a rising trend of work that trains models to natively support more of what the harness does.

This work specifically trains agents to decide for themselves when to compact.

Reminds me of the new paper from Meta https://t.co/DhgVOIdQa4