让大模型更高效地规划网页操作，提升成功率与执行效率。
Plan-MCTS: Plan Exploration for Action Exploitation in Web Navigation
- 将网页导航转化为语义计划空间的树搜索，提升探索效率。
- 在WebArena上任务成功率显著超越现有方法，搜索效率更高。
- 适合需要高可靠性自动网页操作的研究者与开发者。
大型语言模型（LLMs）已使自主代理能够处理复杂的网页导航任务。尽管近期研究通过树搜索增强长程推理能力，但在网页导航中应用此类算法面临两大挑战：有效路径稀疏导致探索效率低下，以及上下文噪声干扰状态感知的准确性。为此，我们提出Plan-MCTS框架，将网页导航重构为语义计划空间中的探索过程。通过解耦战略规划与执行落地，该框架将稀疏的动作空间转化为稠密的计划树以实现高效探索，并将嘈杂上下文提炼为抽象语义历史以实现精准状态感知。为确保效率与鲁棒性，Plan-MCTS引入双重门控奖励机制，严格验证动作的物理可执行性与策略一致性；同时采用结构精炼机制，在策略内修复失败的子计划。在WebArena上的大量实验表明，Plan-MCTS达到当前最优性能，相较现有方法展现出更高的任务有效性与搜索效率。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have empowered autonomous agents to handle complex web navigation tasks. While recent studies integrate tree search to enhance long-horizon reasoning, applying these algorithms in web navigation faces two critical challenges: sparse valid paths that lead to inefficient exploration, and a noisy context that dilutes accurate state perception. To address this, we introduce Plan-MCTS, a framework that reformulates web navigation by shifting exploration to a semantic Plan Space. By decoupling strategic planning from execution grounding, it transforms sparse action space into a Dense Plan Tree for efficient exploration, and distills noisy contexts into an Abstracted Semantic History for precise state awareness. To ensure efficiency and robustness, Plan-MCTS incorporates a Dual-Gating Reward to strictly validate both physical executability and strategic alignment and Structural Refinement for on-policy repair of failed subplans. Extensive experiments on WebArena demonstrate that Plan-MCTS achieves state-of-the-art performance, surpassing current approaches with higher task effectiveness and search efficiency.
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。