---
id: 20260916-T0-04
title: "递归自我改进有了统一形式化框架：一个框架同时描述迭代策略改进与RSI"
title_en: "One Formal Framework Unifies Iterative Policy Improvement and Recursive Self-Improvement"
url: https://ai.daily.yangsir.net/daily/20260916-T0-04
issue_date: 2026-09-16
publish_date: 2026-09-15T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2609.13406
---

# 递归自我改进有了统一形式化框架：一个框架同时描述迭代策略改进与RSI

一篇新论文提出通用智能体迭代框架，试图用一个形式化体系同时描述迭代策略改进和递归自我改进（RSI）。论文指出，当前RSI在多个尺度上被广泛声称，但缺乏统一的形式化描述，导致概念在现象、机制和前景之间混用。该框架的目标是为自主演化智能的研究提供共同语言。属于理论层面的基础工作，短期内不直接产出可用的工程方案。

## English Version

**One Formal Framework Unifies Iterative Policy Improvement and Recursive Self-Improvement**

A new paper proposes a generalized agent iteration framework that formally describes both iterative policy improvement and recursive self-improvement (RSI) under one system. The authors note that RSI is claimed at many scales today but lacks a unified formal description, causing the concept to blur across phenomenon, mechanism, and prospect. The framework aims to give autonomous evolving intelligence research a shared language. It is foundational theory work with no immediate engineering payoff.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2609.13406)

**详情页**：https://ai.daily.yangsir.net/daily/20260916-T0-04

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*