复合AI系统优化：方法、挑战与未来方向综述

摘要

近期，大型语言模型（LLMs）与人工智能系统的重大进展，引领了复杂AI工作流设计与优化的范式转变。通过整合多元组件，复合型AI系统在执行复杂任务方面日益娴熟。然而，随着这些系统复杂度的提升，不仅单个组件的优化面临新挑战，组件间的交互优化也成为了关键问题。尽管监督微调（SFT）和强化学习（RL）等传统优化方法仍占据基础地位，自然语言反馈的兴起为优化不可微系统开辟了前景广阔的新途径。本文系统回顾了复合AI系统优化领域的最新进展，涵盖了数值与基于语言的技术。我们正式定义了复合AI系统优化的概念，沿多个关键维度对现有方法进行了分类，并着重指出了这一快速发展领域中开放的研究挑战与未来方向。所调查论文列表公开于https://github.com/MiuLab/AISysOpt-Survey。

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.

复合AI系统优化：方法、挑战与未来方向综述

Compound AI Systems Optimization: A Survey of Methods, Challenges, and Future Directions

摘要

Support