pith. sign in

We consider two approaches: (a)interruptions, used in works like GLM-4.1V (GLM-V Team et al., 2025), and Qwen3 (Yang et al.,

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

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

The Art of Scaling Reinforcement Learning Compute for LLMs

cs.LG · 2025-10-15 · unverdicted · novelty 7.0

A 400k+ GPU-hour study shows RL scaling in LLMs follows predictable sigmoidal trajectories, with most design choices affecting efficiency rather than the performance asymptote, enabling accurate large-scale predictions via the ScaleRL recipe.

citing papers explorer

Showing 1 of 1 citing paper.

  • The Art of Scaling Reinforcement Learning Compute for LLMs cs.LG · 2025-10-15 · unverdicted · none · ref 32

    A 400k+ GPU-hour study shows RL scaling in LLMs follows predictable sigmoidal trajectories, with most design choices affecting efficiency rather than the performance asymptote, enabling accurate large-scale predictions via the ScaleRL recipe.