AOrchestra：實現智能編排的子代理自動化創建

摘要

語言智慧體在任務自動化方面展現出巨大潛力。為實現應對日益複雜的長週期任務的目標，業界逐漸興起以子智慧體作為工具的多次任務求解範式。然而現有設計仍缺乏對子智慧體的動態抽象視角，從而影響了系統適應性。我們通過提出統一且框架無關的智慧體抽象模型來解決這一挑戰，該模型將任何智慧體表述為（指令、上下文、工具、模型）四元組。此四元組作為能力組合的配方，使系統能按需為每個任務生成專用執行器。基於此抽象模型，我們提出名為AOrchestra的智慧體系統，其核心協調器在每一步驟具體化四元組：策劃任務相關上下文、選擇工具與模型，並通過即時自動創建智慧體進行任務委派。此設計能有效減少人工工程投入，保持框架無關性並提供即插即用式多樣化智慧體支援，同時實現可控的性能-成本權衡，使系統趨近帕累托最優。在三大挑戰性基準測試（GAIA、SWE-Bench、Terminal-Bench）中，AOrchestra搭配Gemini-3-Flash相比最強基準實現了16.28%的相對性能提升。程式碼已開源於：https://github.com/FoundationAgents/AOrchestra

English

Language agents have shown strong promise for task automation. Realizing this promise for increasingly complex, long-horizon tasks has driven the rise of a sub-agent-as-tools paradigm for multi-turn task solving. However, existing designs still lack a dynamic abstraction view of sub-agents, thereby hurting adaptability. We address this challenge with a unified, framework-agnostic agent abstraction that models any agent as a tuple Instruction, Context, Tools, Model. This tuple acts as a compositional recipe for capabilities, enabling the system to spawn specialized executors for each task on demand. Building on this abstraction, we introduce an agentic system AOrchestra, where the central orchestrator concretizes the tuple at each step: it curates task-relevant context, selects tools and models, and delegates execution via on-the-fly automatic agent creation. Such designs enable reducing human engineering efforts, and remain framework-agnostic with plug-and-play support for diverse agents as task executors. It also enables a controllable performance-cost trade-off, allowing the system to approach Pareto-efficient. Across three challenging benchmarks (GAIA, SWE-Bench, Terminal-Bench), AOrchestra achieves 16.28% relative improvement against the strongest baseline when paired with Gemini-3-Flash. The code is available at: https://github.com/FoundationAgents/AOrchestra

AOrchestra：實現智能編排的子代理自動化創建

AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration

摘要

Support