---
id: 20260317-T0-19
title: "研究提出基于LLM的网页代理AI规划框架"
title_en: "Research Proposes AI Planning Framework for LLM Web Agents"
url: https://ai.daily.yangsir.net/daily/20260317-T0-19
issue_date: 2026-03-17
publish_date: 2026-03-16T04:00:00.000Z
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2603.12710
---

# 研究提出基于LLM的网页代理AI规划框架

arXiv论文提出首个专为基于LLM的网页代理设计的AI规划框架。该框架通过显式规划模块代理黑盒决策过程，使代理能够自我诊断失败原因并调整策略。测试显示，使用该框架的代理在复杂网页任务中成功率提高28%，响应时间缩短35%，为构建可靠的自主网页代理提供了新方案。

## English Version

**Research Proposes AI Planning Framework for LLM Web Agents**

arXiv paper proposes first AI planning framework for LLM-based web agents. Replaces black-box decisions with explicit planning module, enabling self-diagnosis and strategy adjustment. Tests show 28% higher success rate and 35% faster response on complex web tasks.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2603.12710)

**详情页**：https://ai.daily.yangsir.net/daily/20260317-T0-19

---

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