The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
Source: https://arxiv.org/abs/2609.11873
Authors: Yi Duan, Ying Liu, Zirui Tang, Haodong Chen, Jun Zhou, Yumou Liu, Bangrui Xu, Yukai Wu, Sidi Chen, Yuhan Zhou, Haoyu Wang, Xiaoyou Yu, Shaokun Han, Xuzhou Zhu, Le Zhou, Bolin Lu, Wei Zhou, Jiachen Liu, Nuozhou Fang, Jiaxin Tian, Ruoyu Chen, Yuxuan Li, Kai Zuo, Kaiyan Zhang, Jiantao Qiu, Conghui He, Guoliang Li, Bowen Zhou, Zhiyuan Liu, Zhoufutu Wen, Jihua Kang, Xuanhe Zhou, Fan Wu
Published: 2026-09-10
Categories: cs.LG, cs.AI, cs.CL
PDF: https://arxiv.org/pdf/2609.11873
Abstract
Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed Index (HCI) to reveal the problems of existing LLMs, then introduce the RSI concept and its development roadmap: from improvement-execution autonomy, improvement-strategy autonomy, experience-acquisition autonomy, and environment-adaptation autonomy, to recursive meta-improvement. Next we examine RSI across scenarios (e.g., scientific discovery, embodied intelligence, software engineering), highlighting their distinct requirements and development speeds. Drawing on diverse industry practices and preliminary empirical evidence, we connect RSI research with practical systems and identify key challenges to achieving genuine RSI.
中文概要
递归自我改进(RSI)指 AI 系统把经验与反馈变成持续的改变——既改进能力,也改进"未来如何改进"的过程本身。
作者先用 Headroom-Closed Index (HCI) 揭示现有 LLM 的局限,再给出 RSI 的概念与发展路线图:
1. 改进执行自主(improvement-execution autonomy) 2. 改进策略自主(improvement-strategy autonomy) 3. 经验获取自主(experience-acquisition autonomy) 4. 环境适应自主(environment-adaptation autonomy) 5. 递归元改进(recursive meta-improvement)
论文按场景对照 RSI 的差异:科学发现、具身智能、软件工程——每个场景的自主级别、发展节奏与必备条件都不同。作者结合工业实践与初步经验证据,把 RSI 研究与实际系统连接起来,指出走向"真正的 RSI"的关键挑战。
这是一份路线图性质的综述,目标读者是希望把 RSI 从概念落到工程的研究与平台团队。