Self-Resource Allocation in Multi-Agent LLM Systems

TL;DR

This paper investigates how large language models can serve as effective resource allocators in multi-agent systems, improving task assignment, coordination, and efficiency through different strategies and explicit worker information.

Contribution

It introduces and compares LLM-based orchestrator and planner methods for resource allocation, highlighting the superiority of planners with explicit worker capability info.

Findings

Planners outperform orchestrators in efficiency and utilization.

LLMs achieve high accuracy in resource allocation tasks.

Explicit worker capability info enhances planner strategies.

Abstract

With the development of LLMs as agents, there is a growing interest in connecting multiple agents into multi-agent systems to solve tasks concurrently, focusing on their role in task assignment and coordination. This paper explores how LLMs can effectively allocate computational tasks among multiple agents, considering factors such as cost, efficiency, and performance. In this work, we address key questions, including the effectiveness of LLMs as orchestrators and planners, comparing their effectiveness in task assignment and coordination. Our experiments demonstrate that LLMs can achieve high validity and accuracy in resource allocation tasks. We find that the planner method outperforms the orchestrator method in handling concurrent actions, resulting in improved efficiency and better utilization of agents. Additionally, we show that providing explicit information about worker capabilities enhances the allocation strategies of planners, particularly when dealing with suboptimal workers.