# Prime Intellect 发布自改进 RLM 框架 Prime Agent

- 来源：🚨 AI News | TestingCatalog (@testingcatalog)
- 发布时间：2026-08-06 07:02
- AIHOT 分数：38
- AIHOT 链接：https://aihot.virxact.com/items/cmsgpdjyi0cksro5q30fo7iga
- 原文链接：https://x.com/testingcatalog/status/2085139367777968229

## AI 摘要

Prime Intellect 推出 Prime Agent，一个面向编码和长时自主任务的自改进 RLM 框架，在 ARC-AGI-3 上得分 95.5%。该框架将上下文视为变量、子代理委派视为 REPL 内的函数调用，并允许代理对其提示词、技能、记忆和子代理状态进行 CRUD 操作，实现自我修改。

## 正文

Prime Intellect announced Prime Agent, a new self-improving RLM harness for coding and long-running autonomous tasks.

Prime Agent scored 95.5% on ARC-AGI-3! 🤯

The Recursive Language Model (RLM) treats context as a variable and subagent delegation as function calls inside a REPL.

Continual Harness treats the harness's own state, abstracted as its prompts, skills, memory, and sub-agents, as something the agent can create, read, update, and delete (CRUD) from its own trajectory.

The next level of abstraction 👀

### 引用推文

> Prime Intellect：Introducing Prime Agent: A self-improving RLM harness for coding and long-running autonomous tasks. Designed to be both token-efficient and expressive through p...