pith. sign in

Improving rl exploration for llm reasoning through retrospective replay

4 Pith papers cite this work. Polarity classification is still indexing.

4 Pith papers citing it

years

2026 3 2025 1

clear filters

representative citing papers

Trust Region On-Policy Distillation

cs.LG · 2026-05-31 · unverdicted · novelty 5.0

TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.

citing papers explorer

Showing 1 of 1 citing paper after filters.