递归组织改进：人机组织的建模规范
原标题：Recursive Organization Improvement: A Modeling Specification for Human--Agent Organizations
AI 摘要
该论文提出「递归组织改进」（ROI）的建模规范，用于描述人机组织中如何评估、保留和修订工作安排，包括修订改进流程本身。作者通过可执行检查器、公开 PR 记录映射和受控仿真进行验证，跨六种决策规则、三种记忆条件和三种任务环境开展机制研究。结果显示，累积证据可提升平衡评估的净价值，但无限期保留证据会在环境反转后延迟适应，而程序替换本身并未带来稳定收益。研究强调证据获取、复用与及时更新需与评估器替换区分开来。
正文节选
Recursive Organization Improvement: A Modeling Specification for Human–Agent Organizations Abstract Stronger AI agents do not automatically produce better organizations: teams must also learn which work arrangements to retain and when to reconsider them. We propose a modeling specification for recursive organization improvement and evaluate it through an executable checker, a public-record mapping, and controlled simulation. The specification connects actor-visible histories, organizational memo