Markovian Thinker

Enable LLMs to scale reasoning length from O(n²) to O(n) by structuring thinking into fixed-size chunks with learnable cross-chunk summaries. Trigger: train reasoning models with unbounded or expensive chain-of-thought sequences.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 4bc9f3adf0

Frequently asked questions

npx get-skill add adu2021/markovian-thinker