Metan：冻结改进机制，逐层加深代码与轨迹实现自我提升
Most self-improving agents still refine answers inside a shallow loop;
Most self-improving agents still refine answers inside a shallow loop;
大多数自我改进的代理仍然在浅层循环中优化答案；
New research from Univ of Minnesota + Seoul Univ takes another route: keep the improver fixed, feed each new layer the code and traces below it, and deepen only while performance improves.
明尼苏达大学和首尔大学的新研究另辟蹊径：保持改进器固定不变，将代码和追踪信息逐层喂给新层，并且仅在性能提升时加深层次。
Instead of letting the agent rewrite the mechanism that improves it, Metan freezes 1 improvement operation and repeatedly asks it to inspect the current solver, its past execution traces, and the improvement code already added, then write a new layer of strategy plus helper functions around the solver.
Metan不是让代理重写改进自身的机制，而是冻结一个改进操作，反复要求它检查当前求解器、其过去的执行追踪以及已添加的改进代码，然后在求解器周围编写新的策略层和辅助函数。
Each new layer therefore has more evidence about what earlier layers tried and whether it worked, so it can refine or even roll back a bad strategy without risking corruption of the improvement mechanism itself.
因此，每一新层都拥有更多关于先前层尝试了什么以及是否成功的证据，从而能够优化甚至回滚不良策略，而不会危及改进机制本身。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力