用多智能体自动优化AI工作流，无需人工干预。
A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback Loops
- 构建五类智能体，通过大模型驱动迭代反馈优化配置。
- 在多个真实场景中提升输出质量、相关性和可操作性。
- 适合需要持续自适应的工业级AI系统开发者。
Agentic AI系统通过专用智能体处理复杂工作流中的任务，实现自动化与高效运作。然而，优化此类系统通常需大量人工调整角色、任务和交互关系。本文提出一种跨行业的自主优化框架，用于提升基于NLP的企业级应用性能。该系统包含精炼、执行、评估、修改和文档化五类智能体，利用大语言模型（Llama 3.2-3B）驱动的迭代反馈循环，自动生成并测试假设以改进系统配置。整个过程无需人工介入即可实现最优性能，显著增强系统的可扩展性与动态环境适应能力。多个领域的案例研究验证了该框架的变革性影响，展示出输出质量、相关性与可操作性的显著提升。所有案例数据，包括原始及演化后的智能体代码及其输出，均可在此获取：https://anonymous.4open.science/r/evolver-1D11/
原文摘要 · Abstract (English)
Agentic AI systems use specialized agents to handle tasks within complex workflows, enabling automation and efficiency. However, optimizing these systems often requires labor-intensive, manual adjustments to refine roles, tasks, and interactions. This paper introduces a framework for autonomously optimizing Agentic AI solutions across industries, such as NLP-driven enterprise applications. The system employs agents for Refinement, Execution, Evaluation, Modification, and Documentation, leveraging iterative feedback loops powered by an LLM (Llama 3.2-3B). The framework achieves optimal performance without human input by autonomously generating and testing hypotheses to improve system configurations. This approach enhances scalability and adaptability, offering a robust solution for real-world applications in dynamic environments. Case studies across diverse domains illustrate the transformative impact of this framework, showcasing significant improvements in output quality, relevance, and actionability. All data for these case studies, including original and evolved agent codes, along with their outputs, are here: https://anonymous.4open.science/r/evolver-1D11/
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。