WebNavigator: 通过交互图检索实现全局网络导航
WebNavigator: Global Web Navigation via Interaction Graph Retrieval
AI总结：
WebNavigator通过交互图检索和路径规划解决自主网络导航中的拓扑盲区问题，实现优于企业级代理的性能。
摘要：
尽管在自主网络导航领域取得了显著进展，当前方法在复杂网络环境中仍远未达到人类水平的性能。我们认为这一局限性源于拓扑盲区，即代理被迫通过试错探索，而无法访问环境的全局拓扑结构。为克服这一局限性，我们引入了WebNavigator，将网络导航从概率性探索重新框架为确定性检索和路径规划。WebNavigator通过零令牌成本启发式探索构建交互图，并在线实现检索-推理-传送的工作流程进行全局导航。WebNavigator在WebArena和OnlineMind2Web上实现了最先进的性能。在WebArena多站点任务中，WebNavigator的成功率为72.9%，超过企业级代理的性能。本工作揭示了拓扑盲区，而非仅模型推理能力，是自主网络导航中被低估的瓶颈。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
