Google's Harness² lifts GLM-5 by 11.5 points
Why it matters
Researchers at Google released Harness², which improves an AI agent by tuning the harness around a frozen model (its prompts, tools, memory and skills) instead of changing the weights. For each task it proposes a general and a domain-specific harness edit, probes both on the same task, and composes a better harness without ground-truth answers, saving lessons to a library for later tasks. On WorkBuddy-Bench one step lifted GLM-5 in OpenCode from 64.2 to 75.7, above base Gemini 3.5 Flash (72.4); gains reached 4.5 points on JobBench and 11.8 percentage points on Harvey's LAB. Caveats: Meta-Harness led on LAB for Gemini 3.5 Flash under Codex, and the extra probe runs add inference cost. Code is Apache 2.0 (arXiv 2610.14224, Oct 9, 2026).
Read the source: arXiv (Harness²) (opens in a new tab)
All hits from 17 Oct 2026More AgentsGet the daily hits by email