让AI自己设计并优化自身，实现持续进化。
Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement
- 用大模型动态修改自身逻辑，按目标自动改进
- 在数学推理任务中表现超越人工设计的智能体
- 适合追求自主进化能力的研究者和开发者
大型语言模型（LLMs）的快速发展显著提升了智能体在各类任务中的能力。然而，现有基于固定流程或预定义元学习框架的智能体系统受限于人工设计的组件，无法全面探索智能体设计空间，可能错过全局最优方案。本文提出Gödel Agent，一个受哥德尔机启发的自演化框架，使智能体无需依赖预设流程或固定优化算法，即可递归地自我改进。该框架利用大模型动态调整自身逻辑与行为，仅通过提示词驱动高阶目标。在数学推理和复杂智能体任务上的实验表明，Gödel Agent能实现持续自我优化，在性能、效率和泛化能力上均优于人工设计的智能体。
原文摘要 · Abstract (English)
The rapid advancement of large language models (LLMs) has significantly enhanced the capabilities of AI-driven agents across various tasks. However, existing agentic systems, whether based on fixed pipeline algorithms or pre-defined meta-learning frameworks, cannot search the whole agent design space due to the restriction of human-designed components, and thus might miss the globally optimal agent design. In this paper, we introduce Gödel Agent, a self-evolving framework inspired by the Gödel machine, enabling agents to recursively improve themselves without relying on predefined routines or fixed optimization algorithms. Gödel Agent leverages LLMs to dynamically modify its own logic and behavior, guided solely by high-level objectives through prompting. Experimental results on mathematical reasoning and complex agent tasks demonstrate that implementation of Gödel Agent can achieve continuous self-improvement, surpassing manually crafted agents in performance, efficiency, and generalizability.
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。