We have 3 of 15 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
This work forms this missing dimension of harness optimization as an automated curriculum learning problem and introduces ActiveSaddler, which establishes automated curriculum learning as a new crucial optimization dimension for harness optimization.
The Prefix-Aware Internal Reward (PAIR), a two-stage model with a frozen hidden-state probe estimating belief-consistency and a lightweight attention-based head correcting it toward grounded correctness, is proposed, enabling dense step-level reward signals for GRPO training without external model calls, ground-truth d...
The proposed AutoSaddler, an automatic harness optimization framework that formulates harness improvement as an offline learning problem and iteratively updates the harness using failure signals from mini-batches, suggests that automatic harness optimization is a promising path toward more performant and reliable agent...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
