AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration
Jianhao Ruan, Zhihao Xu, Yiran Peng, Fashen Ren, Zhaoyang Yu, Xinbing Liang, Jinyu Xiang, Yongru Chen, Bang Liu, Chenglin Wu, Yuyu Luo, Jiayi Zhang

TL;DR
AOrchestra introduces a dynamic, framework-agnostic agent abstraction and system that automates sub-agent creation for complex task orchestration, improving performance and reducing engineering effort.
Contribution
It proposes a unified agent abstraction tuple and a system that dynamically spawns specialized sub-agents, enhancing adaptability and efficiency in task automation.
Findings
Achieves 16.28% improvement on benchmarks with Gemini-3-Flash.
Enables plug-and-play support for diverse agents.
Reduces human engineering efforts in agent orchestration.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMultimodal Machine Learning Applications · Topic Modeling · Multi-Agent Systems and Negotiation
