---
id: 20261110-T0-09
title: "AI代理跨会话不学习？新论文提出持久行为学习框架Decision Context"
title_en: "Decision Context Enables AI Agents to Learn from Corrections Across Sessions"
url: https://ai.daily.yangsir.net/daily/20261110-T0-09
issue_date: 2026-11-10
publish_date: 2026-11-09T05:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2611.08644
---

# AI代理跨会话不学习？新论文提出持久行为学习框架Decision Context

现有LLM代理有一个通病：用户每次开启新对话都得重新纠正同样的错误，因为代理不会跨会话记住纠错行为。已有的代理记忆系统主要处理事实类信息（偏好、实体、对话历史），而非行为模式。论文提出Decision Context方法，让代理把用户的纠正转化为持久的行为规则，在新会话中自动沿用。实际影响是：用户不必反复纠正同一个问题，代理在多轮使用中逐步贴合个人工作习惯。

## English Version

**Decision Context Enables AI Agents to Learn from Corrections Across Sessions**

LLM agents fail to learn from user corrections across sessions, forcing users to repeat the same fixes in every new conversation. Existing agent memory systems store facts—preferences, entities, conversation history—but not behavioral corrections. This paper proposes Decision Context, a framework that turns user corrections into persistent behavioral rules applied automatically in later sessions. The practical result: users stop repeating themselves, and agents converge on individual work habits over repeated use.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2611.08644)

**详情页**：https://ai.daily.yangsir.net/daily/20261110-T0-09

---

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