CMU paper: RL-trained 4B proposer edits agent harness code, beats its 35B teacher

omarsar0 · x · 2026-10-04

A new CMU paper introduces "harness learning": improving agents by editing their harness code instead of their weights.

The authors highlight editing harness code as an emerging AI engineering skill, a shift they see accelerating.

Related event: Harness Learning: 4B Model Rewrites Agent Code, Beats 35B Teacher(3 posts)→

Original post →

More from coding & agent

coding & agent channel →