WebOperator：面向网络环境下自主代理的情境感知树搜索

WebOperator: Action-Aware Tree Search for Autonomous Agents in Web Environment

December 14, 2025

作者: Mahir Labib Dihan, Tanzima Hashem, Mohammed Eunus Ali, Md Rizwan Parvez

cs.AI

摘要

基于大语言模型的智能体通常以贪心的逐步方式运行，仅根据当前观察选择行动而忽略长期后果或替代路径。这种前瞻性缺失在部分可观测的网页环境中尤为突出——由于仅能获取浏览器可见内容（如DOM和UI元素），单个错误操作往往需要通过复杂且脆弱的导航才能撤销。缺乏显式回溯机制使得智能体难以纠正错误或系统化探索替代路径。树搜索方法为这类结构化探索提供了原则性框架，但现有方法缺乏安全回溯机制，容易引发意外副作用，同时假设所有操作皆可逆，忽视了不可逆操作的存在——这些局限降低了其在真实网页任务中的有效性。针对这些挑战，我们提出WebOperator树搜索框架，实现可靠回溯与战略探索。该方法融合了最佳优先搜索策略，通过奖励估计与安全性考量对行动排序，并配备鲁棒的回溯机制，在重放路径前验证其可行性以预防意外副作用。为进一步引导探索，WebOperator从多元推理上下文生成候选行动以确保探索的多样性与鲁棒性，继而通过预执行过滤无效行动与合并语义等价行动来精选高质量行动集。在WebArena和WebVoyager上的实验结果表明了WebOperator的有效性：在WebArena任务中，WebOperator结合gpt-4o实现了54.6%的最优成功率，彰显了战略前瞻与安全执行相结合的关键优势。

English

LLM-based agents often operate in a greedy, step-by-step manner, selecting actions solely based on the current observation without considering long-term consequences or alternative paths. This lack of foresight is particularly problematic in web environments, which are only partially observable-limited to browser-visible content (e.g., DOM and UI elements)-where a single misstep often requires complex and brittle navigation to undo. Without an explicit backtracking mechanism, agents struggle to correct errors or systematically explore alternative paths. Tree-search methods provide a principled framework for such structured exploration, but existing approaches lack mechanisms for safe backtracking, making them prone to unintended side effects. They also assume that all actions are reversible, ignoring the presence of irreversible actions-limitations that reduce their effectiveness in realistic web tasks. To address these challenges, we introduce WebOperator, a tree-search framework that enables reliable backtracking and strategic exploration. Our method incorporates a best-first search strategy that ranks actions by both reward estimates and safety considerations, along with a robust backtracking mechanism that verifies the feasibility of previously visited paths before replaying them, preventing unintended side effects. To further guide exploration, WebOperator generates action candidates from multiple, varied reasoning contexts to ensure diverse and robust exploration, and subsequently curates a high-quality action set by filtering out invalid actions pre-execution and merging semantically equivalent ones. Experimental results on WebArena and WebVoyager demonstrate the effectiveness of WebOperator. On WebArena, WebOperator achieves a state-of-the-art 54.6% success rate with gpt-4o, underscoring the critical advantage of integrating strategic foresight with safe execution.