发现信息
- 作者:Hao Wu, Fan Xu, Fan Zhang, Zhipeng Xu, Yantao Zhang, Yinghui Li, Yizhou Zhao, Penghao Zhao
- 年份:2026
- 发表源:Preprints.org
- OpenAlex ID:https://openalex.org/W7215072796
- DOI:https://doi.org/10.20944/preprints202609.2680.v1
- arXiv:待核验
- 检索主题:recursive-improvement
- OpenAlex 引用数快照:1(2026-11-12)
摘要线索
Recursive self-improvement (RSI) seeks to turn gains in an AI system into a stronger capacity to produce subsequent gains. Foundation models make parts of this process practical through generated training data, program revision and automated experimentation, but repeated optimization alone does not establish recursive improvement. This survey organizes the field around two overlapping goals: automated design of AI infrastructure, and repair and optimization of existing systems. We relate these goals to AutoML, meta-learning and program search, and formulate their objectives alongside criteria for task gains, retained capabilities and improved update procedures. A common account of update targets, feedback, inheritance and external control connects self-training, memory and skills, agent design, editable improvers and automated research. We synthesize methods by shared mechanisms and compare their evidence under independent testing, resource controls, transfer probes and multi-round evaluation. Existing studies show that systems can retain useful changes and, in limited settings, improve how they produce subsequent updates. They do not yet establish unrestricted or reliably accelerating self-improvement. We identify feedback quality, interacting updates and independent validation as central constraints, and develop testable directions for more reliable, transferable improvement loops.
核验与筛选
- 当前状态:待筛选、去重和一手来源核验。
- OpenAlex 元数据和引用数只用于发现,不作为正式引文或质量判断。
- 记录正式版本、venue、方法细节、实验协议和局限后,才迁入稳定论文卡片。