HAWK: A Hierarchical Workflow Framework for Multi-Agent Collaboration

TL;DR

Hawk introduces a modular hierarchical framework that enhances multi-agent collaboration through standardized interfaces, adaptive scheduling, and resource abstraction, improving scalability, efficiency, and flexibility across diverse domains.

Contribution

The paper presents HAWK, a novel layered framework with standardized interfaces and adaptive scheduling, enabling scalable and flexible multi-agent systems with heterogeneous components.

Findings

Demonstrated scalability and effectiveness with CreAgentive prototype

Achieved higher throughput and lower invocation complexity

Showed seamless integration of large language models within HAWK

Abstract

Contemporary multi-agent systems encounter persistent challenges in cross-platform interoperability, dynamic task scheduling, and efficient resource sharing. Agents with heterogeneous implementations often lack standardized interfaces; collaboration frameworks remain brittle and hard to extend; scheduling policies are static; and inter-agent state synchronization is insufficient. We propose Hierarchical Agent Workflow (HAWK), a modular framework comprising five layers-User, Workflow, Operator, Agent, and Resource-and supported by sixteen standardized interfaces. HAWK delivers an end-to-end pipeline covering task parsing, workflow orchestration, intelligent scheduling, resource invocation, and data synchronization. At its core lies an adaptive scheduling and optimization module in the Workflow Layer, which harnesses real-time feedback and dynamic strategy adjustment to maximize utilization. The Resource Layer provides a unified abstraction over heterogeneous data sources, large models, physical devices, and third-party services&tools, simplifying cross-domain information retrieval. We demonstrate HAWK's scalability and effectiveness via CreAgentive, a multi-agent novel-generation prototype, which achieves marked gains in throughput, lowers invocation complexity, and improves system controllability. We also show how hybrid deployments of large language models integrate seamlessly within HAWK, highlighting its flexibility. Finally, we outline future research avenues-hallucination mitigation, real-time performance tuning, and enhanced cross-domain adaptability-and survey prospective applications in healthcare, government, finance, and education.