Google Harness²：递归智能体框架自我改进

"Harness^2: Recursive Agent Harnessing for an Open World"

Harness optimization would usually struggle to adapt to new tasks without ground-truth feedback, and improvements made for one task rarely transfer to others too.

So Google's Harness² introduces two levels of recursive self-improvement: it proposes, tests, and combines changes to an agent's prompts, tools, and workflows for the current task, then stores lessons from those experiments to improve future harness modifications.

Across GLM-5 and Gemini 3.5 Flash, it improves performance by up to 11.5% on WorkBuddy-Bench, 4.5% on JobBench, and 11.8% on Legal Agent Bench, without updating model weights.

https://alphaxiv.org/abs/2610.14224