综述论文梳理递归自我改进 AI 的 5 个等级：完整 RSI 尚未到来
一篇把递归自我改进拆成 5 级的综述，看完能分清现在哪些是真 RSI、哪些只是流程自动化，L5 还卡在哪。
这篇综述论文把递归自我改进（RSI）拆成 5 个等级，从执行人类设计的改进，到更改后续轮次的改进器、评估器或研究策略。结论是目前已有的"自我改进 AI"大多只自动化了改进流程的部分环节，还无法改进"如何改进"这一机制本身。论文指出 AI 在回答知识与推理问题上很强，但在涉及工具、软件和变化环境的长链条多步任务上明显偏弱。L5 的端到端证据目前仍集中在有限范围的原型系统里。
Beautiful roadmap paper on Recursive self-improvement.
Concludes, we are already seeing pieces of RSI, but full recursive self-improvement is not here yet.
Most self-improving AI still cannot improve how it improves
Says that most things called "self-improving AI" today only automate parts of the improvement process.
Genuine recursive self-improvement would mean the AI can persistently improve not just its outputs, prompts, tools, or code, but eventually the mechanism that decides how future improvements are discovered, tested, and kept.
AI is already very strong at answering knowledge and reasoning questions, but still much weaker at doing long, multi-step tasks with tools, software, and changing environments.
The paper maps progress across 5 levels, from executing human-designed improvements to changing the improver, evaluator, or research policy used in later rounds.
That last step makes the process recursive: a successful update changes how future updates are discovered or judged.
The survey finds broad evidence for lower levels, while experience-driven learning and deployment adaptation are more domain-dependent and end-to-end L5 evidence remains concentrated in bounded prototypes.
