以下为上游提供的源文稿,可能存在识别错误。
乔木转写是基于源文稿的中文提炼,不是逐字翻译。请核对原文中的人名、数字与观点。
选一篇,慢慢读
从左侧挑一篇,正文会在这里排成书页。
Harness optimization is often studied with a fixed policy model and benchmark. When either changes, the optimizer must decide which parts of an evolved harness to reuse or revise, but the harness alone may not explain why earlier edits were made or how they performed. In this work, we study Continual Recursive Self-Imp
阅读原文 · Xin Yu, Fei Xia, Jiaqi Pan, Youbao Tang, Chengzhi Liu, Adams Yu, Sicong Jiang, Yanfei Chen, Lingzhou Xue, Ting Yu
向阳乔木 · opencode-go/deepseek-v4.1-flash
这篇论文关注一个很实际的问题:当我们用大模型自动优化一套“脚手架”(论文里叫 harness,可以理解为包在模型外面的提示词、工具调用流程、解析规则、重试逻辑等一整套工程配置),如果换了模型或者换了评测集,之前那轮优化留下的东西,哪些该继承、哪些该推翻? 只保留最终那套 harness,信息是不够的。因为没人记得当初为什么这么改、改完效果如何。这篇论文提出给...