Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909623730044928 |
|---|---|
| author | Qiu, Jiahao Qi, Xuan Zhang, Tongcheng Juan, Xinzhe Guo, Jiacheng Lu, Yifu Wang, Yimin Yao, Zixin Ren, Qihan Jiang, Xun Zhou, Xing Liu, Dongrui Yang, Ling Wu, Yue Huang, Kaixuan Liu, Shilong Wang, Hongru Wang, Mengdi |
| author_facet | Qiu, Jiahao Qi, Xuan Zhang, Tongcheng Juan, Xinzhe Guo, Jiacheng Lu, Yifu Wang, Yimin Yao, Zixin Ren, Qihan Jiang, Xun Zhou, Xing Liu, Dongrui Yang, Ling Wu, Yue Huang, Kaixuan Liu, Shilong Wang, Hongru Wang, Mengdi |
| contents | Recent advances in large language models (LLMs) have enabled agents to autonomously perform complex, open-ended tasks. However, many existing frameworks depend heavily on manually predefined tools and workflows, which hinder their adaptability, scalability, and generalization across domains. In this work, we introduce Alita--a generalist agent designed with the principle of "Simplicity is the ultimate sophistication," enabling scalable agentic reasoning through minimal predefinition and maximal self-evolution. For minimal predefinition, Alita is equipped with only one component for direct problem-solving, making it much simpler and neater than previous approaches that relied heavily on hand-crafted, elaborate tools and workflows. This clean design enhances its potential to generalize to challenging questions, without being limited by tools. For Maximal self-evolution, we enable the creativity of Alita by providing a suite of general-purpose components to autonomously construct, refine, and reuse external capabilities by generating task-related model context protocols (MCPs) from open source, which contributes to scalable agentic reasoning. Notably, Alita achieves 75.15% pass@1 and 87.27% pass@3 accuracy, which is top-ranking among general-purpose agents, on the GAIA benchmark validation dataset, 74.00% and 52.00% pass@1, respectively, on Mathvista and PathVQA, outperforming many agent systems with far greater complexity. More details will be updated at $\href{https://github.com/CharlesQ9/Alita}{https://github.com/CharlesQ9/Alita}$. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20286 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution Qiu, Jiahao Qi, Xuan Zhang, Tongcheng Juan, Xinzhe Guo, Jiacheng Lu, Yifu Wang, Yimin Yao, Zixin Ren, Qihan Jiang, Xun Zhou, Xing Liu, Dongrui Yang, Ling Wu, Yue Huang, Kaixuan Liu, Shilong Wang, Hongru Wang, Mengdi Artificial Intelligence Recent advances in large language models (LLMs) have enabled agents to autonomously perform complex, open-ended tasks. However, many existing frameworks depend heavily on manually predefined tools and workflows, which hinder their adaptability, scalability, and generalization across domains. In this work, we introduce Alita--a generalist agent designed with the principle of "Simplicity is the ultimate sophistication," enabling scalable agentic reasoning through minimal predefinition and maximal self-evolution. For minimal predefinition, Alita is equipped with only one component for direct problem-solving, making it much simpler and neater than previous approaches that relied heavily on hand-crafted, elaborate tools and workflows. This clean design enhances its potential to generalize to challenging questions, without being limited by tools. For Maximal self-evolution, we enable the creativity of Alita by providing a suite of general-purpose components to autonomously construct, refine, and reuse external capabilities by generating task-related model context protocols (MCPs) from open source, which contributes to scalable agentic reasoning. Notably, Alita achieves 75.15% pass@1 and 87.27% pass@3 accuracy, which is top-ranking among general-purpose agents, on the GAIA benchmark validation dataset, 74.00% and 52.00% pass@1, respectively, on Mathvista and PathVQA, outperforming many agent systems with far greater complexity. More details will be updated at $\href{https://github.com/CharlesQ9/Alita}{https://github.com/CharlesQ9/Alita}$. |
| title | Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2505.20286 |