Google paper: gated self-improving agent harnesses cut token cost 10x and transfer across models

omarsar0 · x · 2026-11-18

Swerling observability is out; harness engineering is in. A new Google paper, "Harnesses That Improve Themselves," proposes a framework where an optimizer rewrites the agent runtime around a frozen model.

Key results on SWE-bench Lite (frozen Gemini 3.8 Flash):

The gated approach splits the harness into four editable components — context, control, tools, verification — patches one per round, validates on held-out tasks under a token cap, and deploys only if it passes.

It also transferred to Gemini 4 Argon with no new search (37.5% vs 30.0% for full rewrite). Caveat: only 40 held-out issues, so treat numbers as directional. The paper catalogs failure modes of self-modification, including prompt bloat, benchmark gaming, and evaluator tampering.

Original post →

More from coding & agent

coding & agent channel →