Notas del episodio
Fixing Reasoning from Three Directions at OnceLLMs Research Podcast | Episode: Feb 1–6, 2026
DeepSeek-R1 made RL the default approach for reasoning. This episode covers the 30 papers from the first week of February that are debugging what that approach got wrong, across training geometry, pipeline design, reward signals, memory architecture, and inference efficiency.
Timestamps
[00:00] Opening and framing — The post-DeepSeek hangover: why the field has shifted from scaling RL to fixing it. Three camps emerge: geometricians, pipeline engineers, and architects.
[01:11] MRPO and the bias…
Web: llmsresearch.substack.com

