Google's GUARD paper: frozen base model, self-editing agent harness gains +8.89 points

omarsar0 · x · 2026-11-19

Google Cloud researchers published 'GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance', targeting the classic failure modes of self-improving agent harnesses: local overfitting, catastrophic forgetting, and memory pollution.

Core idea

Key results

At test time a single frozen harness runs in one pass, offering a practical grader-free RSI path where weight-space RL is impractical.

Original post →

More from coding & agent

coding & agent channel →