BLOG
Posts / 02
Method notes from ongoing research.
HarnessOPD: Keeping the Behavioral Gains of a Stronger Harness Inside the Model↗
A stronger search-agent harness can improve decisions, but the gains may vanish once those components are removed. HarnessOPD studies how to keep part of that advantage in the model parameters.
Research note
RG-CTO: Letting Failure Experience Influence the Next Attempt Selectively↗
Failed traces should not be reused wholesale. RG-CTO estimates the reliability of negative experience before deciding how strongly it may shape generation.
Research note
No matching posts. Try another keyword or topic.