# 智能体持续学习：超越模型参数的适配

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-08-22 07:25
- AIHOT 分数：36
- AIHOT 链接：https://aihot.virxact.com/items/cmt3lo9v10vhjro6tfdznqvof
- 原文链接：https://x.com/rohanpaul_ai/status/2090943348081307932

## AI 摘要

一篇新论文提出“框架持续学习”（HCL）框架，指出智能体无需重训模型，仅通过重写自身提示词、记忆和路由即可实现行为更新。论文将模型冻结而周边行为持续变化的现象称为“框架级遗忘”，并主张对提示词、记忆、技能和路由的改动应像代码变更一样进行回归测试后再持久化。

## 正文

An agent can improve without retraining the model.

Once agents rewrite their own prompts, memory, and routing, every update becomes a behavioral change.

As agents keep rewriting prompts, memories, skills, and routing rules, those updates become part of what the system has learned.

Fixing today's failure can quietly break something that worked yesterday.

The paper calls this harness-level forgetting: the model stays frozen, but the behavior around it keeps changing.

Their Harness Continual Learning (HCL) framework puts every proposed harness update behind a gate.

For evolving agents, prompt, memory, skill, and routing changes should be handled like code changes: regression-test them before they become persistent.

– arxiv. org/abs/2608.19013

Title: "Harness Continual Learning: Continual Adaptation Beyond Model Parameters"