WebOperator：面向网络环境中自主代理的情境感知树搜索

摘要

基於大語言模型的智能體通常以貪婪的逐步方式運行，僅根據當前觀測選擇行動而忽略長期後果或替代路徑。這種前瞻性缺失在部分可觀測的網絡環境中尤為突出——此類環境僅限於瀏覽器可見內容（如DOM和UI元素）——單次操作失誤往往需要複雜且脆弱的導航才能撤銷。若缺乏顯式回溯機制，智能體難以糾正錯誤或系統性探索替代路徑。樹搜索方法為此類結構化探索提供了理論框架，但現有方法缺少安全回溯機制，易導致非預期副作用。它們還假設所有操作皆可逆，忽略了不可逆操作的存在——這些侷限性降低了其實際網絡任務中的有效性。為應對這些挑戰，我們提出WebOperator這一支持可靠回溯與策略性探索的樹搜索框架。該方法融合了最佳優先搜索策略（通過獎勵估計與安全性考量對行動排序）與魯棒回溯機制（在重放路徑前驗證其可行性以預防副作用）。為進一步引導探索，WebOperator從多樣化推理上下文生成行動候選集以確保探索的多元性與穩健性，並通過預執行過濾無效操作及合併語義等價操作來提煉高質量行動集。在WebArena和WebVoyager上的實驗結果驗證了WebOperator的有效性：在WebArena中，WebOperator憑藉gpt-4o實現了54.6%的頂尖成功率，彰顯了策略性前瞻與安全執行的關鍵優勢。

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.

WebOperator：面向网络环境中自主代理的情境感知树搜索

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

摘要

Support