MemGUI-Agent：一種端到端長時域移動圖形使用者介面代理，具備主動上下文管理

摘要

基於多模態大語言模型（MLLM）的行動裝置GUI智能體在短期任務上已取得顯著進展，但在需要跨多步驟與應用轉換間保留中間事實的長期任務上仍不可靠。我們將此限制歸因於ReAct風格的提示方式——該方式被動累積每一步的記錄，導致提示爆炸並稀釋關鍵的跨應用事實。為解決此問題，我們提出MemGUI-Agent，一種具備主動式上下文管理的端到端長期行動裝置GUI智能體。MemGUI-Agent建立在「上下文即行動」（Context-as-Action, ConAct）的概念上，該概念將上下文管理視為與選取UI行動相同策略所發出的第一級行動。不同於被動附加歷史記錄，ConAct維護三個結構化的上下文欄位：摺疊操作歷史、摺疊UI狀態與近期步驟記錄，在保留關鍵UI事實的同時保持上下文精簡。為使主動式上下文管理能在不同模型規模下學習，我們建構了MemGUI-3K資料集，包含2,956條完整ConAct註解的軌跡，可用於監督訓練與離線分析。在MemGUI-3K上訓練的8B模型產生了MemGUI-8B-SFT，這款8B MemGUI-Agent在MemGUI-Bench上達到了公開數據中最佳的8B效能，並可泛化至分佈外基準MobileWorld。程式碼、資料與訓練模型將於https://memgui-agent.github.io/公開發布。

English

MLLM-based mobile GUI agents have made substantial progress on short-horizon tasks, yet remain unreliable on long-horizon tasks that require retaining intermediate facts across many steps and app transitions. We attribute this limitation to ReAct-style prompting, which passively accumulates per-step records, leading to prompt explosion and dilution of critical cross-app facts. To address this, we introduce MemGUI-Agent, an end-to-end long-horizon mobile GUI agent with proactive context management. MemGUI-Agent is built on Context-as-Action (ConAct), which casts context management as first-class actions emitted by the same policy that selects UI actions. Instead of passively appending history, ConAct maintains three structured context fields: folded action history, folded UI state, and recent step record, preserving critical UI facts while keeping context compact. To make proactive context management learnable across model scales, we construct MemGUI-3K, a 2,956-trajectory dataset with full ConAct annotations for supervised training and offline analysis. Training an 8B model on MemGUI-3K produces MemGUI-8B-SFT, an 8B MemGUI-Agent that achieves the best open-data 8B performance on MemGUI-Bench and generalizes to the out-of-distribution MobileWorld benchmark. Code, data, and trained models will be released at https://memgui-agent.github.io/.