Salvato in:
| Autori principali: | , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2507.11988 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915394864807936 |
|---|---|
| author | Shi, Yexuan Wang, Mingyu Cao, Yunxiang Lai, Hongjie Lan, Junjian Han, Xin Wang, Yu Geng, Jie Li, Zhenan Xia, Zihao Chen, Xiang Li, Chen Xu, Jian Duan, Wenbo Zhu, Yuanshuo |
| author_facet | Shi, Yexuan Wang, Mingyu Cao, Yunxiang Lai, Hongjie Lan, Junjian Han, Xin Wang, Yu Geng, Jie Li, Zhenan Xia, Zihao Chen, Xiang Li, Chen Xu, Jian Duan, Wenbo Zhu, Yuanshuo |
| contents | Multi-Agent Systems (MAS) powered by Large Language Models (LLMs) are emerging as a powerful paradigm for solving complex, multifaceted problems. However, the potential of these systems is often constrained by the prevalent plan-and-execute framework, which suffers from critical limitations: rigid plan execution, static agent capabilities, and inefficient communication. These weaknesses hinder their adaptability and robustness in dynamic environments. This paper introduces Aime, a novel multi-agent framework designed to overcome these challenges through dynamic, reactive planning and execution. Aime replaces the conventional static workflow with a fluid and adaptive architecture. Its core innovations include: (1) a Dynamic Planner that continuously refines the overall strategy based on real-time execution feedback; (2) an Actor Factory that implements Dynamic Actor instantiation, assembling specialized agents on-demand with tailored tools and knowledge; and (3) a centralized Progress Management Module that serves as a single source of truth for coherent, system-wide state awareness. We empirically evaluated Aime on a diverse suite of benchmarks spanning general reasoning (GAIA), software engineering (SWE-bench Verified), and live web navigation (WebVoyager). The results demonstrate that Aime consistently outperforms even highly specialized state-of-the-art agents in their respective domains. Its superior adaptability and task success rate establish Aime as a more resilient and effective foundation for multi-agent collaboration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_11988 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Aime: Towards Fully-Autonomous Multi-Agent Framework Shi, Yexuan Wang, Mingyu Cao, Yunxiang Lai, Hongjie Lan, Junjian Han, Xin Wang, Yu Geng, Jie Li, Zhenan Xia, Zihao Chen, Xiang Li, Chen Xu, Jian Duan, Wenbo Zhu, Yuanshuo Artificial Intelligence Multi-Agent Systems (MAS) powered by Large Language Models (LLMs) are emerging as a powerful paradigm for solving complex, multifaceted problems. However, the potential of these systems is often constrained by the prevalent plan-and-execute framework, which suffers from critical limitations: rigid plan execution, static agent capabilities, and inefficient communication. These weaknesses hinder their adaptability and robustness in dynamic environments. This paper introduces Aime, a novel multi-agent framework designed to overcome these challenges through dynamic, reactive planning and execution. Aime replaces the conventional static workflow with a fluid and adaptive architecture. Its core innovations include: (1) a Dynamic Planner that continuously refines the overall strategy based on real-time execution feedback; (2) an Actor Factory that implements Dynamic Actor instantiation, assembling specialized agents on-demand with tailored tools and knowledge; and (3) a centralized Progress Management Module that serves as a single source of truth for coherent, system-wide state awareness. We empirically evaluated Aime on a diverse suite of benchmarks spanning general reasoning (GAIA), software engineering (SWE-bench Verified), and live web navigation (WebVoyager). The results demonstrate that Aime consistently outperforms even highly specialized state-of-the-art agents in their respective domains. Its superior adaptability and task success rate establish Aime as a more resilient and effective foundation for multi-agent collaboration. |
| title | Aime: Towards Fully-Autonomous Multi-Agent Framework |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2507.11988 |