让网页智能体像人一样记路、复盘，提升导航准确率和任务完成率。
R2D2: Remembering, Replaying and Dynamic Decision Making with a Reflective Agentic Memory
- 用记忆缓冲区动态重建网页结构，生成访问过的页面地图。
- 导航错误减少50%，任务完成率提升至三倍以上。
- 适合需要长期记忆与自我优化的自动化交互系统。
网络智能体在复杂网页环境中执行任务时，常因视野有限和对网页结构理解不足而表现不佳。本文提出的R2D2框架融合两种机制：记忆（Remember）与反思（Reflect）。记忆机制通过回放缓冲区动态重建网页环境，帮助智能体构建已访问页面的详细“地图”，从而降低导航错误并优化决策。反思机制则通过分析历史错误，实现策略迭代与性能提升。在WebArena基准测试中，R2D2显著优于现有方法，导航错误降低50%，任务完成率提高三倍。结果表明，结合增强记忆的导航与反思学习，可有效提升网页智能体能力，适用于自动客服、个人数字助理等场景。
原文摘要 · Abstract (English)
The proliferation of web agents necessitates advanced navigation and interaction strategies within complex web environments. Current models often struggle with efficient navigation and action execution due to limited visibility and understanding of web structures. Our proposed R2D2 framework addresses these challenges by integrating two paradigms: Remember and Reflect. The Remember paradigm uses a replay buffer that aids agents in reconstructing the web environment dynamically, thus enabling the formulation of a detailed "map" of previously visited pages. This helps in reducing navigational errors and optimizing the decision-making process during web interactions. Conversely, the Reflect paradigm allows agents to learn from past mistakes by providing a mechanism for error analysis and strategy refinement, enhancing overall task performance. We evaluate R2D2 using the WebArena benchmark, demonstrating substantial improvements over existing methods, including a 50% reduction in navigation errors and a threefold increase in task completion rates. Our findings suggest that a combination of memory-enhanced navigation and reflective learning promisingly advances the capabilities of web agents, potentially benefiting various applications such as automated customer service and personal digital assistants.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。