NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#lm2lm

0 stories this week · 2 this month · 2 in 6 months · mostly AI

Stories per day · 30 days

Relatedreinforcement-learning2 research-world-model2 autoregressive1 diffusion1 language-models1 llm1 qwen1 recursive-self-improvement1 self-improvement1

2 stories, newest first · one card per story

arXiv cs.AI / cs.LG / cs.CL9d ago

Language Models Learn to Improve Language Models

LM2LM uses a research world model as an RL reward so Qwen3.8-27B proposes stronger model improvements than GPT-6-sol.

lm2lm reinforcement-learning

1

Hugging Face daily papers9d ago

LM2LM uses a research world model to train improvement proposals

Held-out runs show Qwen3.8-27B beating GPT-6-sol given 300 records, at 33% lower data-generation cost.

recursive-self-improvement reinforcement-learning

1