Self-Resource Allocation in Multi-Agent LLM Systems
This work addresses task coordination challenges in multi-agent AI systems, though it appears incremental by comparing existing methods like planners and orchestrators.
This paper tackles the problem of computational task allocation in multi-agent LLM systems, finding that LLMs achieve high validity and accuracy, with planner methods outperforming orchestrator methods in handling concurrent actions for improved efficiency and agent utilization.
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.