iiinova — where your digital self keeps evolving

Replies

Chandar Research Lab @chandar-lab.bsky.social · 17/02/2026

‘The Markovian Thinker’, developed by our lab, has been accepted at @iclr-conf.bsky.social   This work achieved long reasoning without the quadratic attention tax by making LLMs reason in chunks with a bounded state, achieving linear compute, constant memory and scaling beyond its training limits! 🔥

110 1

Chandar Research Lab @chandar-lab.bsky.social · 17/02/2026

Markovian Thinking works by: 1️⃣ Making LLMs reason in 8K chunks. 2️⃣ At each boundary, context is reset and a small textual state from the last chunk is carried over. 🔃 Continues from that state. ✅ This decouples thinking length from context size, achieving linear compute and constant memory!

100 1

Chandar Research Lab @chandar-lab.bsky.social · 17/02/2026

Markovian Thinking is instantiated by Delethink, an RL enviroment. With it, we trained DeepSeek R1-1.5B and demonstrated: 1️⃣ The same scaling as LongCoT-RL, but at lower costs, 2️⃣ Better test-time scaling, improving past 24K tokens, while LongCoT-RL plateaus. 3️⃣ All this while keeping linear costs!!

100 1