6. The Markovian Thinker

A new RL thinking environment that keeps an LLM’s effective state constant by chunking long chains of thought and carrying over only a short textual state between chunks.https://t.co/mqXfF1XG6h

— DAIR.AI (@dair_ai) 12 octobre 2025

6. The Markovian Thinker A new RL thinking environment that keeps an LLM’s effective state constant by chunking long chains of thought and carrying over only a short textual state between chunks.

→ View original post on X — @dair_ai