Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-08-29 · source-backed
ES achieves broader reasoning coverage, with verifier-projected Jensen-Shannon diversity across the ES population theoretically tied to higher Pass@K, and empirically improves Pass@1 while reaching higher Pass@K where GRPO collapses entropy. The proposed sequential GRPO-then-ES schedule keeps GRPO's Pass@1 and adds ES's Pass@K. Two side findings: despite large whole-model parameter drift, gains come from a sparse subset of larger-magnitude updates, and larger LLMs need a smaller ES population. (arXiv)
Each link below shares sources, entities, or timing with this story.
Unsloth released GRPO / Shared entity: GRPO / Earlier coverage / Tension
Linked by a graph relationship (Unsloth released GRPO); both cover GRPO; earlier GRPO coverage from 2026-06-20.
Shannon built by Anthropic / Shared entity: LLMs / Same source domain / Earlier coverage / Tension
Linked by a graph relationship (Shannon built by Anthropic); both cover LLMs; reported by the same outlet (arxiv.org).
Unsloth released GRPO / Shared entity: LLMs / Earlier coverage
Linked by a graph relationship (Unsloth released GRPO); both cover LLMs; earlier LLMs coverage from 2026-08-13.
Unsloth released GRPO
Linked by a graph relationship (Unsloth released GRPO).
Linked by a graph relationship (Unsloth released GRPO).
Shannon built by Anthropic / Shared entity: Pass / Same source domain / Earlier coverage
Linked by a graph relationship (Shannon built by Anthropic); both cover Pass; reported by the same outlet (arxiv.org).
Shannon built by Anthropic / Shared entity: LLMs / Same source domain / Earlier coverage
Linked by a graph relationship (Shannon built by Anthropic); both cover LLMs; reported by the same outlet (arxiv.org).
Shannon built by Anthropic / Shared entity: Pass / Same source domain / Earlier coverage
Linked by a graph relationship (Shannon built by Anthropic); both cover Pass; reported by the same outlet (arxiv.org).