EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms
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_ | 1866915189005221888 |
|---|---|
| author | Yuan, Siyu Song, Kaitao Chen, Jiangjie Tan, Xu Li, Dongsheng Yang, Deqing |
| author_facet | Yuan, Siyu Song, Kaitao Chen, Jiangjie Tan, Xu Li, Dongsheng Yang, Deqing |
| contents | The rise of powerful large language models (LLMs) has spurred a new trend in building LLM-based autonomous agents for solving complex tasks, especially multi-agent systems. Despite the remarkable progress, we notice that existing works are heavily dependent on human-designed frameworks, which greatly limits the functional scope and scalability of agent systems. How to automatically extend the specialized agent to multi-agent systems to improve task-solving capability still remains a significant challenge. In this paper, we introduce EvoAgent, a generic method to automatically extend specialized agents to multi-agent systems via the evolutionary algorithm, thereby improving the effectiveness of LLM-based agents in solving tasks. Specifically, we consider the existing agent frameworks as the initial individual and then apply a series of evolutionary operators (e.g., mutation, crossover, selection, etc.) to generate multiple agents with diverse settings. Experimental results across various tasks show that EvoAgent can significantly enhance the task-solving capability of LLM-based agents, and can be generalized to any LLM-based agent framework to extend them into multi-agent systems. Resources are available at https://evo-agent.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_14228 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms Yuan, Siyu Song, Kaitao Chen, Jiangjie Tan, Xu Li, Dongsheng Yang, Deqing Artificial Intelligence The rise of powerful large language models (LLMs) has spurred a new trend in building LLM-based autonomous agents for solving complex tasks, especially multi-agent systems. Despite the remarkable progress, we notice that existing works are heavily dependent on human-designed frameworks, which greatly limits the functional scope and scalability of agent systems. How to automatically extend the specialized agent to multi-agent systems to improve task-solving capability still remains a significant challenge. In this paper, we introduce EvoAgent, a generic method to automatically extend specialized agents to multi-agent systems via the evolutionary algorithm, thereby improving the effectiveness of LLM-based agents in solving tasks. Specifically, we consider the existing agent frameworks as the initial individual and then apply a series of evolutionary operators (e.g., mutation, crossover, selection, etc.) to generate multiple agents with diverse settings. Experimental results across various tasks show that EvoAgent can significantly enhance the task-solving capability of LLM-based agents, and can be generalized to any LLM-based agent framework to extend them into multi-agent systems. Resources are available at https://evo-agent.github.io/. |
| title | EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2406.14228 |