系统梳理复杂AI系统优化方法，涵盖语言反馈与传统技术。
Compound AI Systems Optimization: A Survey of Methods, Challenges, and Future Directions
- 提出复合AI系统优化的统一框架，分类现有方法
- 对比语言反馈与传统微调在非可微系统中的效果
- 适合关注AI工作流设计的研究者和工程师
大语言模型和AI系统的发展推动了复杂AI工作流设计与优化范式的转变。通过整合多个组件，复合AI系统在执行复杂任务方面日益成熟。然而，随着系统复杂度提升，不仅个体组件需要优化，其交互关系也面临新挑战。尽管监督微调（SFT）和强化学习（RL）仍是基础方法，自然语言反馈的兴起为优化不可微系统提供了新路径。本文系统回顾了复合AI系统优化的最新进展，涵盖数值型与基于语言的技术。我们形式化了复合AI系统优化的概念，从多个关键维度对现有方法进行分类，并指出现有研究挑战与未来方向。相关论文列表可在 https://github.com/MiuLab/AISysOpt-Survey 公开获取。
原文摘要 · Abstract (English)
Recent advancements in large language models (LLMs) and AI systems have led to a paradigm shift in the design and optimization of complex AI workflows. By integrating multiple components, compound AI systems have become increasingly adept at performing sophisticated tasks. However, as these systems grow in complexity, new challenges arise in optimizing not only individual components but also their interactions. While traditional optimization methods such as supervised fine-tuning (SFT) and reinforcement learning (RL) remain foundational, the rise of natural language feedback introduces promising new approaches, especially for optimizing non-differentiable systems. This paper provides a systematic review of recent progress in optimizing compound AI systems, encompassing both numerical and language-based techniques. We formalize the notion of compound AI system optimization, classify existing methods along several key dimensions, and highlight open research challenges and future directions in this rapidly evolving field. A list of surveyed papers is publicly available at https://github.com/MiuLab/AISysOpt-Survey.
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。