用视觉定位+显式记忆，让网页导航智能体不再迷路。
See and Remember: A Multimodal Agent for Web Traversal
- 通过视觉定位解决按钮等元素歧义，结合显式记忆栈跟踪路径。
- 在复杂网页任务中实现28.7%的性能提升，避免循环导航错误。
- 适合需要长期记忆与精准操作的自动化网页任务场景。
自主网页导航要求智能体感知复杂视觉环境并维持长期上下文，但现有基于大语言模型的智能体常出现空间迷失和导航循环。本文提出通用的V-GEMS（视觉定位与显式记忆系统）架构，通过视觉定位消除交互元素歧义，并引入带状态追踪的显式记忆堆栈，构建结构化导航路径图，实现有效回溯，防止深层任务中的循环失败。我们还设计了可更新的动态基准以严格评估适应性。实验表明，V-GEMS显著优于WebWalker基线，性能提升达28.7%。代码已公开于https://github.com/Vaultttttttttttt/V-GEMS。
原文摘要 · Abstract (English)
Autonomous web navigation requires agents to perceive complex visual environments and maintain long-term context, yet current Large Language Model (LLM) based agents often struggle with spatial disorientation and navigation loops. In this paper, we propose generally applicable V-GEMS(Visual Grounding and Explicit Memory System), a robust multimodal agent architecture designed for precise and resilient web traversal. Our agent integrates visual grounding to resolve ambiguous interactive elements and introduces an explicit memory stack with state tracking. This dual mechanism allows the agent to maintain a structured map of its traversal path, enabling valid backtracking and preventing cyclical failures in deep navigation tasks. We also introduce an updatable dynamic benchmark to rigorously evaluate adaptability. Experiments show V-GEMS significantly dominates the WebWalker baseline, achieving a substantial 28.7% performance gain. Code is available at https://github.com/Vaultttttttttttt/V-GEMS.
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。