Self-Resource Allocation in Multi-Agent LLM Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909585533566976 |
|---|---|
| author | Amayuelas, Alfonso Yang, Jingbo Agashe, Saaket Nagarajan, Ashwin Antoniades, Antonis Wang, Xin Eric Wang, William |
| author_facet | Amayuelas, Alfonso Yang, Jingbo Agashe, Saaket Nagarajan, Ashwin Antoniades, Antonis Wang, Xin Eric Wang, William |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02051 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-Resource Allocation in Multi-Agent LLM Systems Amayuelas, Alfonso Yang, Jingbo Agashe, Saaket Nagarajan, Ashwin Antoniades, Antonis Wang, Xin Eric Wang, William Multiagent Systems Artificial Intelligence Computation and Language 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. |
| title | Self-Resource Allocation in Multi-Agent LLM Systems |
| topic | Multiagent Systems Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2504.02051 |