Hugging Face 开源 Reef：面向持续自我改进智能体的推理基础设施
原标题：Your Inference Server is Secretly a Learner: Reef Infrastructure for Continual Self-Improving Agents
AI 摘要
Hugging Face 开源了 Reef 基础设施，旨在让智能体（harness + 模型）能够从经验中持续自我进化。Reef 以推理为核心，提供标准 OpenAI 格式推理端点，并将推理轨迹、执行结果和用户反馈存储为结构化经验流，支持模型权重与 harness（提示、记忆、技能、工具、编排逻辑）的联合更新。其目标是让开源社区更容易实验持续自我改进，并获得生产级基础设施。
正文节选
Your Inference Server is Secretly a Learner: Reef Infrastructure for Continual Self-Improving Agents Before today's excitement around RSI is fully realized, we want to open-source Reef, an infrastructure we've been building for the same broader problem: enabling agents (harness + model) to continuously evolve from their experience. The goal is to make it easier for the open-source community to experiment with continual self-improvement and readily access production-grade infrastructure for it. W