【GLM披露国内首个RSI工程实践】记者获悉，今日，GLM团队披露了在递归自我改进方向的首个工程化实践，由GLM-5.3驱动的Infra Agent完成了GLM-5.3-Flash推理基础设施的设计、调试与优化，实现模型对自身运行系统的反向改进。这是国内大模型厂商首次公开跑进生产环境的RSI案例。据官方博客，Infra Agent在超10万张国产芯片组成的集群上从零完成生产级推理服务搭建，不到两周将端到端吞吐提升至初始基线的3倍，硬件利用效率与单Token成本达到主流NVIDIA GPU相当水平，并支持1M上下文窗口与多模态请求。该系统已经受真实流量检验，GLM-5.3-Flash以匿名模型Ox-Alpha在OpenCode、OpenRouter上线，6天Token调用量超过62万亿。此次实践的技术突破在于，Agent已不再局限于生成代码，而是能够围绕推理系统开展完整的工程闭环：自主分析性能瓶颈、定位精度缺陷、修改底层代码、执行分层测试，并根据实验反馈持续迭代。GLM团队表示，系统尚未达到完全自主设计和训练下一代模型的阶段，但RSI的早期形态已经出现，即，模型建设推理系统，系统再反过来支撑模型运行。
Disclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.