MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916765714350080 |
|---|---|
| author | Wang, Qian Wang, Tianyu Tang, Zhenheng Li, Qinbin Chen, Nuo Liang, Jingsheng He, Bingsheng |
| author_facet | Wang, Qian Wang, Tianyu Tang, Zhenheng Li, Qinbin Chen, Nuo Liang, Jingsheng He, Bingsheng |
| contents | LLM-based multi-agent systems (MAS) have shown promise in tackling complex tasks. However, existing solutions often suffer from limited agent coordination and heavy reliance on predefined Standard Operating Procedures (SOPs), which demand extensive human input. To address these limitations, we propose MegaAgent, a large-scale autonomous LLM-based multi-agent system. MegaAgent generates agents based on task complexity and enables dynamic task decomposition, parallel execution, efficient communication, and comprehensive system monitoring of agents. In evaluations, MegaAgent demonstrates exceptional performance, successfully developing a Gobang game within 800 seconds and scaling up to 590 agents in a national policy simulation to generate multi-domain policies. It significantly outperforms existing systems, such as MetaGPT, in both task completion efficiency and scalability. By eliminating the need for predefined SOPs, MegaAgent demonstrates exceptional scalability and autonomy, setting a foundation for advancing true autonomy in MAS. Our code is available at https://github.com/Xtra-Computing/MegaAgent . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_09955 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs Wang, Qian Wang, Tianyu Tang, Zhenheng Li, Qinbin Chen, Nuo Liang, Jingsheng He, Bingsheng Multiagent Systems LLM-based multi-agent systems (MAS) have shown promise in tackling complex tasks. However, existing solutions often suffer from limited agent coordination and heavy reliance on predefined Standard Operating Procedures (SOPs), which demand extensive human input. To address these limitations, we propose MegaAgent, a large-scale autonomous LLM-based multi-agent system. MegaAgent generates agents based on task complexity and enables dynamic task decomposition, parallel execution, efficient communication, and comprehensive system monitoring of agents. In evaluations, MegaAgent demonstrates exceptional performance, successfully developing a Gobang game within 800 seconds and scaling up to 590 agents in a national policy simulation to generate multi-domain policies. It significantly outperforms existing systems, such as MetaGPT, in both task completion efficiency and scalability. By eliminating the need for predefined SOPs, MegaAgent demonstrates exceptional scalability and autonomy, setting a foundation for advancing true autonomy in MAS. Our code is available at https://github.com/Xtra-Computing/MegaAgent . |
| title | MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2408.09955 |