Self-evolving agent framework Épi hits 120 research records, tightens Klarner's constant

my_cat_can_code · x · 2026-09-16

A team introduces Épi, a self-evolving framework for autonomous research. Running in verifiable environments on sandbox infrastructure, Épi's agents produced 120 record-setting results in just a few days across mathematics, quantum information, operations research, and engineering optimization. Highlights:

The authors frame this as turning compute into verifiable research improvement — and say they're just getting started.

Original post →

More from coding & agent

coding & agent channel →