pith. sign in

New skills or sharper primitives? a probabilistic perspective on the emergence of reasoning in rlvr.arXiv preprint arXiv:2602.08281,

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Predictable GRPO: A Closed-Form Model of Training Dynamics

cs.LG · 2026-06-29 · unverdicted · novelty 7.0

A closed-form inertial model of GRPO dynamics that subsumes single-exponential saturation as its overdamped limit and predicts group-size invariance, stability thresholds, and overdamped-to-oscillatory transitions.

citing papers explorer

Showing 1 of 1 citing paper.

  • Predictable GRPO: A Closed-Form Model of Training Dynamics cs.LG · 2026-06-29 · unverdicted · none · ref 11

    A closed-form inertial model of GRPO dynamics that subsumes single-exponential saturation as its overdamped limit and predicts group-size invariance, stability thresholds, and overdamped-to-oscillatory transitions.