Test-time compute scaling for agents isn’t just running multiple full trajectories and picking a winner. Duplicate a 50–150 step workflow and you multiply tool calls, latency, and cost.

Our take: allocate compute at high-uncertainty steps + use strong reducers to close the… pic.twitter.com/IG4Q240iTr

— AI21 Labs (@AI21Labs) 5 mars 2026

Test-time compute scaling for agents isn’t just running multiple full trajectories and picking a winner. Duplicate a 50–150 step workflow and you multiply tool calls, latency, and cost. Our take: allocate compute at high-uncertainty steps + use strong reducers to close the

→ View original post on X — @ai21labs,