arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.22386cs.AIcs.CL
收藏

从静态模板到动态运行时图:LLM代理工作流优化的综述

From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents

Department of Computer Science, Rensselaer Polytechnic Institute(伦斯勒理工学院计算机科学系);IBM Research(IBM研究院);Department of Mechanical, Aerospace, and Nuclear Engineering, Rensselaer Polytechnic Institute(伦斯勒理工学院机械、航空航天与核工程系)

Ling Yue, Kushal Raj Bhandari, Ching-Yun Ko, Dhaval Patel, Shuxin Lin, Nianjun Zhou, Jianxi Gao, Pin-Yu Chen, Shaowu Pan

AI总结:

本文综述了LLM代理工作流优化方法,区分静态与动态方法,探讨结构确定时间、优化部分及评估信号,提出结构感知评估视角以提升可比性和可复现性。

摘要:

大型语言模型(LLM)基于系统因能通过构建可执行工作流来解决任务而日益流行,此类工作流交织了LLM调用、信息检索、工具使用、代码执行、内存更新和验证。本文综述了近期用于设计和优化此类工作流的方法,将其视为代理计算图(ACGs)。我们根据工作流结构确定的时间组织文献,结构指组件或代理的存在、彼此之间的依赖关系以及信息流动。此视角区分静态方法,即在部署前固定可重用的工作流框架,与动态方法,即在特定运行前或执行中选择、生成或修订工作流。我们进一步根据结构确定时间、优化工作流的哪一部分以及指导优化的评估信号(如任务指标、验证器信号、偏好或跟踪衍生反馈)组织先前工作。我们还区分可重用的工作流模板、运行特定的实现图和执行跟踪,将可重用的设计选择与给定运行中实际部署的结构和实现运行时行为分开。最后,我们概述了结构感知评估视角,以补充下游任务指标,包括图级属性、执行成本、鲁棒性和输入间的结构变化。我们的目标是提供清晰的术语、统一的框架以定位新方法、更可比的现有文献观点以及更可复现的评估标准,以促进未来LLM代理工作流优化的研究。

英文摘要:

Large language model (LLM)-based systems are becoming increasingly popular for solving tasks by constructing executable workflows that interleave LLM calls, information retrieval, tool use, code execution, memory updates, and verification. This survey reviews recent methods for designing and optimizing such workflows, which we treat as agentic computation graphs (ACGs). We organize the literature based on when workflow structure is determined, where structure refers to which components or agents are present, how they depend on each other, and how information flows between them. This lens distinguishes static methods, which fix a reusable workflow scaffold before deployment, from dynamic methods, which select, generate, or revise the workflow for a particular run before or during execution. We further organize prior work along three dimensions: when structure is determined, what part of the workflow is optimized, and which evaluation signals guide optimization (e.g., task metrics, verifier signals, preferences, or trace-derived feedback). We also distinguish reusable workflow templates, run-specific realized graphs, and execution traces, separating reusable design choices from the structures actually deployed in a given run and from realized runtime behavior. Finally, we outline a structure-aware evaluation perspective that complements downstream task metrics with graph-level properties, execution cost, robustness, and structural variation across inputs. Our goal is to provide a clear vocabulary, a unified framework for positioning new methods, a more comparable view of existing body of literature, and a more reproducible evaluation standard for future work in workflow optimizations for LLM agents.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑