**AOrchestra：面向智能体编排的自动化子智能体生成框架**

摘要

语言智能体在任务自动化方面展现出巨大潜力。为实现处理日益复杂的长期任务这一目标，子智能体即工具范式应运而生，用于多轮次任务求解。然而，现有设计仍缺乏对子智能体的动态抽象视角，从而影响系统适应性。我们通过提出统一的框架无关型智能体抽象模型解决这一挑战，该模型将任意智能体表征为四元组（指令、上下文、工具、模型）。该四元组作为能力组合的配方，使系统能够按需为每个任务生成专用执行器。基于此抽象模型，我们推出智能体化系统AOrchestra，其核心协调器在每一步动态实例化四元组：策划任务相关上下文、选择工具与模型、通过实时自动创建智能体实现任务委派。这种设计能有效减少人工工程成本，保持框架无关性并支持即插即用的多样化智能体作为任务执行器。同时支持可控的性能-成本权衡，使系统趋近帕累托最优。在三大挑战性基准测试（GAIA、SWE-Bench、Terminal-Bench）中，AOrchestra配合Gemini-3-Flash相比最强基线实现16.28%的相对性能提升。代码已开源：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：面向智能体编排的自动化子智能体生成框架

AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration

摘要

Support