通过构建交互图实现全局网页导航，突破传统探索瓶颈
WebNavigator: Global Web Navigation via Interaction Graph Retrieval
- 离线构建交互图，线上通过检索-推理-瞬移实现精准导航
- 在WebArena多站点任务中达72.9%成功率，性能翻倍于企业级代理
- 适合研究自主导航、复杂环境路径规划的学者与开发者
尽管自主网页导航取得显著进展，现有方法在复杂网络环境中仍远未达到人类水平。我们指出，其局限性源于拓扑盲区——代理在缺乏全局结构信息的情况下只能通过试错探索。为此，我们提出WebNavigator，将网页导航从概率性探索转变为确定性检索与路径规划。WebNavigator通过零成本启发式离线探索构建交互图，并在线上实施检索-推理-瞬移工作流实现全局导航。在WebArena和OnlineMind2Web基准上，WebNavigator均达当前最优表现。在WebArena多站点任务中，成功率达72.9%，性能超过企业级代理两倍以上。本工作揭示，拓扑盲区而非模型推理能力本身，是自主网页导航中被低估的关键瓶颈。
原文摘要 · Abstract (English)
Despite significant advances in autonomous web navigation, current methods remain far from human-level performance in complex web environments. We argue that this limitation stems from Topological Blindness, where agents are forced to explore via trial-and-error without access to the global topological structure of the environment. To overcome this limitation, we introduce WebNavigator, which reframes web navigation from probabilistic exploration into deterministic retrieval and pathfinding. WebNavigator constructs Interaction Graphs via zero-token cost heuristic exploration offline and implements a Retrieve-Reason-Teleport workflow for global navigation online. WebNavigator achieves state-of-the-art performance on WebArena and OnlineMind2Web. On WebArena multi-site tasks, WebNavigator achieves a 72.9\% success rate, more than doubling the performance of enterprise-level agents. This work reveals that Topological Blindness, rather than model reasoning capabilities alone, is an underestimated bottleneck in autonomous web navigation.
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。