DynTaskMAS: A Dynamic Task Graph-driven Framework for Asynchronous and Parallel LLM-based Multi-Agent Systems
This work addresses efficiency and scalability issues for developers building LLM-based multi-agent systems, though it appears incremental as it builds on existing frameworks with new mechanisms.
The paper tackles the problem of resource management, task coordination, and efficiency in LLM-based multi-agent systems by introducing DynTaskMAS, a framework that uses dynamic task graphs for asynchronous and parallel operations, resulting in a 21-33% reduction in execution time, a 35.4% improvement in resource utilization, and near-linear throughput scaling up to 16 concurrent agents.
The emergence of Large Language Models (LLMs) in Multi-Agent Systems (MAS) has opened new possibilities for artificial intelligence, yet current implementations face significant challenges in resource management, task coordination, and system efficiency. While existing frameworks demonstrate the potential of LLM-based agents in collaborative problem-solving, they often lack sophisticated mechanisms for parallel execution and dynamic task management. This paper introduces DynTaskMAS, a novel framework that orchestrates asynchronous and parallel operations in LLM-based MAS through dynamic task graphs. The framework features four key innovations: (1) a Dynamic Task Graph Generator that intelligently decomposes complex tasks while maintaining logical dependencies, (2) an Asynchronous Parallel Execution Engine that optimizes resource utilization through efficient task scheduling, (3) a Semantic-Aware Context Management System that enables efficient information sharing among agents, and (4) an Adaptive Workflow Manager that dynamically optimizes system performance. Experimental evaluations demonstrate that DynTaskMAS achieves significant improvements over traditional approaches: a 21-33% reduction in execution time across task complexities (with higher gains for more complex tasks), a 35.4% improvement in resource utilization (from 65% to 88%), and near-linear throughput scaling up to 16 concurrent agents (3.47X improvement for 4X agents). Our framework establishes a foundation for building scalable, high-performance LLM-based multi-agent systems capable of handling complex, dynamic tasks efficiently.