The authors represent a prompt's pass rate, p, using the arc-length coordinate ψ = arcsin√p on the Fisher-Rao geometry of Bernoulli outcomes.
Fisher-Rao prompt curricula make GRPO training more rollout-efficient
ARCUS selects prompts in a statistically natural pass-rate coordinate, improving mathematical reasoning accuracy while using substantially fewer model rollouts.
Top University
Mei Okonkwo · Pixel Nomand · Julian Berg · Elena Voss · Lena Park · Marcus Hale · +2 more
University of Wisconsin–Madison · University of Washington
Research Digest··2 min read
Okonkwo et al.
Why this paper
From University of Washington and University of Wisconsin–Madison
In one line
ARCUS reduces GRPO rollouts by 48-57% and improves accuracy by 2.8-2.9 points using Fisher-Rao arc length for prompt selection.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§