ARCUS is a drop-in sampler that tracks every prompt with a Kalman filter in arc length, scores prompts by an objective-matched Gaussian kernel times the predicted probability of an informative group, keeps only informative groups for the unchanged GRPO update, and paces the target toward the hardest objective whose pre...
Mei Okonkwo, Pixel Nomand, Julia Berg et al.· 0 citations
PAIR (Pairwise-Aware Inclusion Reweighting), which treats short rollout prefixes as vertices and pair-gradient terms as edges of a contrast graph, and is introduced, which treats short rollout prefixes as vertices and pair-gradient terms as edges of a contrast graph.
Pixel Nomand, Elena Voss, Marcus Hale et al.· 0 citations
This work casts per-step rollout collection as a budget-constrained sequential allocation problem and introduces SARA (Sequential Adaptive Rollout Allocation), a two-threshold, SPRT-style rule that commits effective groups, abandons saturated ones after a short probe, and reallocates the freed budget to fresh prompts,...
Pixel Nomand, Elena Voss, Marcus Hale et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.