UFO^3：編織數位智慧體星系

摘要

基於大語言模型（LLM）的智能體正將數位設備從被動工具轉變為主動的智能協作夥伴。然而現有框架多侷限於單一作業系統或設備，導致跨設備工作流程脆弱且高度依賴人工操作。我們提出UFO^3系統，該系統將異構終端設備（桌面端、伺服器、移動設備及邊緣計算節點）統一整合為協同調度架構。UFO^3將用戶請求建模為可演化的任務星群（TaskConstellation）：通過具象化控制流與數據流依賴關係（TaskStarLines），構建由原子化子任務（TaskStars）組成的分散式有向無環圖（DAG）。隨著分散式設備的結果流持續輸入，任務星群動態演化，實現非同步執行、自適應恢復與動態優化。星群協調器（Constellation Orchestrator）在實施動態DAG更新的同時安全非同步執行任務，而智能體交互協議（AIP）則為可靠任務分派與結果流傳輸提供持久化低延遲通道。這些設計打破了設備與平台間的傳統壁壘，使智能體能夠無縫協作並增強群體智能。我們在NebulaBench基準測試集（包含5台設備、10個類別的55項跨設備任務）上評估UFO^3。實驗結果顯示：UFO^3實現83.3%的子任務完成率與70.9%的整體任務成功率，平均並行寬度達1.72，端到端延遲較順序執行基準降低31%。故障注入實驗表明，系統在瞬態與永久性智能體故障下均能實現優雅的性能降級與恢復。這些結果證實UFO^3可實現精準、高效、韌性的跨異構設備任務協調，將孤立智能體整合為貫穿普適計算場景的連貫自適應計算框架。

English

Large language model (LLM)-powered agents are transforming digital devices from passive tools into proactive intelligent collaborators. However, most existing frameworks remain confined to a single OS or device, making cross-device workflows brittle and largely manual. We present UFO^3, a system that unifies heterogeneous endpoints, desktops, servers, mobile devices, and edge, into a single orchestration fabric. UFO^3 models each user request as a mutable TaskConstellation: a distributed DAG of atomic subtasks (TaskStars) with explicit control and data dependencies (TaskStarLines). The TaskConstellation continuously evolves as results stream in from distributed devices, enabling asynchronous execution, adaptive recovery, and dynamic optimization. A Constellation Orchestrator} executes tasks safely and asynchronously while applying dynamic DAG updates, and the Agent Interaction Protocol (AIP) provides persistent, low-latency channels for reliable task dispatch and result streaming. These designs dissolve the traditional boundaries between devices and platforms, allowing agents to collaborate seamlessly and amplify their collective intelligence. We evaluate UFO^3 on NebulaBench, a benchmark of 55 cross-device tasks across 5 machines and 10 categories. UFO^3 achieves 83.3% subtask completion, 70.9% task success, exposes parallelism with an average width of 1.72, and reduces end-to-end latency by 31% relative to a sequential baseline. Fault-injection experiments demonstrate graceful degradation and recovery under transient and permanent agent failures. These results show that UFO^3 achieves accurate, efficient, and resilient task orchestration across heterogeneous devices, uniting isolated agents into a coherent, adaptive computing fabric that extends across the landscape of ubiquitous computing.

UFO^3：編織數位智慧體星系

UFO^3: Weaving the Digital Agent Galaxy

摘要

Support