Your Agent Needs to Remember What Passed

Thu, 22 Oct 2026 00:00:00 +0000

TL;DR: Ten pieces, 1% odds each. Guess all ten at once and you need about 10^20 tries. Keep each piece a check confirms and you need about 1,000. In agent loops, the model raises the odds that a change is useful, and a verifier plus a memory of accepted changes turns those odds into progress. The numbers come from a toy model with independent pieces, fixed odds, a check that spots every real improvement, and kept pieces that later changes don’t break. Real tasks bend those assumptions, so build the verifier first.

The two previous posts in this series looked at the checking side of an agent loop. Generate-and-Verify [2] paired an expensive guess with a cheap, trustworthy check. Self-Consistency [3] repeated a guess and took a vote. Neither post looked closely at what the loop keeps between attempts. This post does.

schristoph.online

Your Agent Needs to Remember What Passed