Alita用极简设计实现智能体自主进化，不依赖人工工具也能高效解题。
Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution
- 仅用一个核心组件直接解决问题，大幅简化传统复杂流程。
- 在GAIA基准上达到75.15%的pass@1准确率，领先同类通用智能体。
- 能自动构建和复用外部能力，适合需要自适应推理的开放任务场景。
大型语言模型的进步使智能体能够自主执行复杂、开放的任务。然而，许多现有框架高度依赖手动预定义的工具与工作流，限制了其适应性、可扩展性和跨领域泛化能力。本文提出Alita——一种遵循“简约即极致”原则的通用智能体，通过极简预定义与最大自演化实现可扩展的智能推理。在极简设计方面，Alita仅配备一个用于直接求解问题的核心组件，远比依赖大量手工设计工具和流程的方法更简洁，增强了对复杂问题的泛化潜力。在自演化方面，通过提供一系列通用组件，Alita可自主生成任务相关的模型上下文协议（MCPs），从开源资源中构建、优化并复用外部能力，推动可扩展的智能推理。值得注意的是，Alita在GAIA基准验证集上达到75.15% pass@1和87.27% pass@3准确率，位居通用智能体前列；在Mathvista和PathVQA上分别取得74.00%和52.00% pass@1，优于许多结构更复杂的系统。
原文摘要 · Abstract (English)
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 $\href{https://github.com/CharlesQ9/Alita}{https://github.com/CharlesQ9/Alita}$.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。