做 AI 自我改进研究的团队终于有了可对照的评估框架——DGM 的 80 轮迭代提升数据值得参考，建议用 MetaAI-Mini 协议复现验证。
这篇论文提出了 MetaAI 递归自设计的操作化证据框架，包含四个标准：可检查的目标系统、元级修改器、反馈导向选择和递归延续。作者将 DGM、STOP、Goedel Agent 和 ShinkaEvolve 等公开系统映射到该框架上，其中 DGM 提供了最直接的证据：经过 80 次迭代，SWE-bench Verified 从 20% 提升到 50%，Polyglot 从 14.2% 提升到 30.7%。消融实验表明开放探索和自我改进都有贡献。论文还提供了 MetaAI-Mini，一个基于 HumanEval 的可复现协议和代码库，但目前尚未包含完整模型运行结果。这项工作为 AI 自我改进提供了系统化的评估方法。
From 0-to-1 to 1-to-N: Reproducible Engineering Evidence for MetaAI Recursive Self-Design
Recursive self-design refers to AI-assisted modification of the mechanisms by which an AI system is built, evaluated, and improved. This paper treats MetaAI not as a mature paradigm, but as a working term for a human-seeded, AI-expanded development pattern in which the design space itself becomes a target of modification. We propose an operational evidence framework with four criteria: inspectable target system, meta-level modifier, feedback-directed selection, and recursive continuation. We then map public systems, including Darwin Goedel Machine (DGM), STOP, Goedel Agent, and ShinkaEvolve, against these criteria. DGM provides the most direct currently reported evidence: its published results show improvement from 20% to 50% on SWE-bench Verified and from 14.2% to 30.7% on full Polyglot after 80 iterations, with ablations suggesting that both open-ended exploration and self-improvement contribute. Finally, we provide MetaAI-Mini, a reproducible HumanEval-based protocol and codebase. Because no completed model run is included in this build, MetaAI-Mini is reported as a protocol rather than as an experimental result.