Google Research 开源 Harness²：让智能体自我改进提示词与工作流
Google 把自家让智能体自动改提示词、调工具、攒经验的框架开源了，不改模型本身就能越用越好，做智能体的可以直接拿来试。
Google Research 开源了 Harness² 框架。该框架让 AI 智能体自行优化提示词、工具、记忆和工作流配置。
它会测试不同配置组合，把有效的经验保留下来用于后续任务。整个过程中底层模型保持不变，改进发生在模型外围的系统层。
Google Research has open-sourced Harness², a framework that enables AI agents to improve their own prompts, tools, memory, and workflows. It tests different configurations and carries useful lessons into future tasks while keeping the underlying model unchanged.
An increasing number of releases concerning self-improving models are being published.
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Google, Harness², 智能体, 提示词工程.
Source attribution: curated from kimmonismus (@kimmonismus).
