ENTITY On-Policy Self-Training

On-Policy Self-Training

PulseAugur coverage of On-Policy Self-Training — every cluster mentioning On-Policy Self-Training across labs, papers, and developer communities, ranked by signal.

Show in brief

Total · 30d

1 over 90d

Releases · 30d

0 over 90d

Papers · 30d

1 over 90d

TIER MIX · 90D

TOPICS

infra 1
paper 1
model release 1

TIMELINE

2026-10-26 research_milestone A new paper details On-Policy Self-Training (O-ST), a method for large language models to learn from their own generated outputs without external data, outperforming RLHF. source

SENTIMENT · 30D

1 day(s) with sentiment data

RECENT · PAGE 1/1 · 1 TOTAL

TOOL · CL_323488 · Oct 26 · 18:47

70B Model Learns Without External Data, Outperforms RLHF

A new paper introduces On-Policy Self-Training (O-ST), a method where a 70-billion-parameter model learns from its own generated outputs and reasoning traces without external data. This self-training approach reportedly…

70B Model Learns Without External Data, Outperforms RLHF