Dream-RSI：通过演化世界实现递归自我改进

AI 摘要

该论文提出 Dream-RSI 框架，通过将历史发现记录构建为回放模拟器，让探索策略在离线环境中获得低成本反馈并持续改进，从而减少昂贵的在线评估。改进后的策略再部署到线上驱动新发现，形成递归自我改进循环。在算法工程、数学优化和 GPU 内核工程任务上，该方法在保持或提升发现质量的同时显著降低了发现成本。

正文节选

Dream-RSI: Recursive Self-Improvement through Evolving Worlds Abstract Dream-RSI enables scalable recursive self-improvement by using historical discovery replay to evaluate exploration policies offline, reducing costly online evaluations. Recursive self-improvement is becoming increasingly vital for autonomous AI agents, where progress hinges on discovering high-value solutions across complex domains. The driver of this process is effective exploration, however, managing and improving explorati

发布时间：—

抓取时间：2026-09-15 14:26

来源机构：Hugging Face