自动创建专用智能体，让任务执行更灵活高效。
AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration
- 将智能体抽象为指令、上下文、工具、模型四元组，实现动态生成。
- 在三个基准上使用Gemini-3-Flash时，相比最强基线提升16.28%。
- 无需人工设计，支持多种框架，适合复杂长程任务场景。
语言智能体在任务自动化方面展现出巨大潜力。面对日益复杂的长周期任务，现有方法采用子智能体作为工具的范式，但缺乏对子智能体的动态抽象，影响适应性。本文提出统一且框架无关的智能体抽象方式，将任意智能体建模为四元组（指令、上下文、工具、模型），作为能力的组合配方，使系统可按需生成专用执行器。基于此抽象，构建了智能体编排系统AOrchestra：中心协调器在每一步动态构建该四元组，筛选任务相关上下文，选择工具与模型，并通过即时自动创建智能体来委派执行。该设计显著降低人工工程成本，兼容多种框架，支持即插即用的智能体集成。同时支持可控的性能-成本权衡，逼近帕累托最优。在GAIA、SWE-Bench、Terminal-Bench三个挑战性基准上，搭配Gemini-3-Flash时，相对最强基线取得16.28%的相对提升。代码已开源。
原文摘要 · Abstract (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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。