← Tuesday, October 20, 2026AgentsPaper

Harness² improves agent harnesses recursively without ground-truth feedback

github.com 4 min read Editor score 8/10

Harness² uses task-level Propose–Probe–Compose refinement and a persistent harness that carries lessons forward; one step improved results by up to 11.8 percentage points across the reported benchmarks. The method offers evidence on improving agent behavior while keeping model weights fixed.

What

Harness² is a plug-and-play framework that recursively improves agent harnesses while keeping model weights fixed.

Method

Task-level recursion proposes, probes, and composes harness edits without ground-truth feedback; harnessing-level recursion carries adopted harnesses and lessons forward.

Why it matters

The reported benchmark gains show how agent behavior can be improved by iterating on prompts, tools, memory, and other harness components rather than retraining weights.

Read on github.com → Hacker News · 18 comments

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.