AgentOrchestra: A Hierarchical Multi-Agent Framework for General-Purpose Task Solving

2025-06-14 · Wentao Zhang, Ce Cui, Yilei Zhao, Rui Hu, Yang Liu, Yahui Zhou, Bo An

Recent advances in agent systems based on large language models (LLMs) have demonstrated strong capabilities in solving complex tasks. However, most current methods lack mechanisms for coordinating specialized agents and have limited ability to generalize to new or diverse domains. We introduce \projectname, a hierarchical multi-agent framework for general-purpose task solving that integrates high-level planning with modular agent collaboration. Inspired by the way a conductor orchestrates a symphony and guided by the principles of \textit{extensibility}, \textit{multimodality}, \textit{modularity}, and \textit{coordination}, \projectname features a central planning agent that decomposes complex objectives and delegates sub-tasks to a team of specialized agents. Each sub-agent is equipped with general programming and analytical tools, as well as abilities to tackle a wide range of real-world specific tasks, including data analysis, file operations, web navigation, and interactive reasoning in dynamic multimodal environments. \projectname supports flexible orchestration through explicit sub-goal formulation, inter-agent communication, and adaptive role allocation. We evaluate the framework on three widely used benchmark datasets covering various real-world tasks, searching web pages, reasoning over heterogeneous modalities, etc. Experimental results demonstrate that \projectname consistently outperforms flat-agent and monolithic baselines in task success rate and adaptability. These findings highlight the effectiveness of hierarchical organization and role specialization in building scalable and general-purpose LLM-based agent systems.

📄 PDF Abstract BibTeX arXiv:2506.12508

Code (1)

skyworkai/deepresearchagent 공식 구현

Learning Structured Communication for Multi-agent Reinforcement Learning

2020-02-11 · Junjie Sheng, Xiangfeng Wang, Bo Jin, Junchi Yan 외

This work explores the large-scale multi-agent communication mechanism under a multi-agent reinforcement learning (MARL) setting. We summarize the general categories of topology for communication structures in MARL liter…

Graph Neural Network Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Modelling Bounded Rationality in Multi-Agent Interactions by Generalized Recursive Reasoning

2019-01-26 · Ying Wen, Yaodong Yang, Rui Luo, Jun Wang

Though limited in real-world decision making, most multi-agent reinforcement learning (MARL) models assume perfectly rational agents -- a property hardly met due to individual's cognitive limitation and/or the tractabili…

Decision Making Multi-agent Reinforcement Learning Reinforcement Learning

Generative World Models of Tasks: LLM-Driven Hierarchical Scaffolding for Embodied Agents

2025-09-05 · Brennen Hill arxiv

Recent advances in agent development have focused on scaling model size and raw interaction data, mirroring successes in large language models. However, for complex, long-horizon multi-agent tasks such as robotic soccer,…

Multi-agent Reinforcement Learning

OrgAgent: Organize Your Multi-Agent System like a Company

2026-04-01 · Yiru Wang, Xinyue Shen, Yaohui Han, Michael Backes 외 arxiv

While large language model-based multi-agent systems have shown strong potential for complex reasoning, how to effectively organize multiple agents remains an open question. In this paper, we introduce OrgAgent, a compan…

Hierarchical GNN-Based Multi-Agent Learning for Dynamic Queue-Jump Lane and Emergency Vehicle Corridor Formation

2026-01-07 · Haoran Su arxiv

Emergency vehicles require rapid passage through congested traffic, yet existing strategies fail to adapt to dynamic conditions. We propose a novel hierarchical graph neural network (GNN)-based multi-agent reinforcement …

Multi-agent Reinforcement Learning Graph Neural Network