大語言模型代理時代的圖工程：從個體智能到系統智能

摘要

大型語言模型（LLM）已從語言生成器演化為能執行複雜、長時程任務的自主智能體。此一演化催生了多種範式，包括用以激發模型能力的提示工程（Prompt Engineering）、用以管理資訊存取的上下文工程（Context Engineering）、用以組織外部工具與資源的整合工程（Harness Engineering），以及用以支援持續反思與自我改進的迴圈工程（Loop Engineering）。然而，隨著任務日益複雜，個體智能面臨根本限制：許多任務需要異質專業知識、相互依賴的子任務、平行執行、獨立驗證與持久狀態，這些皆超出任何單一智能體的組織能力。僅擴充單一智能體的能力或上下文，無法解決這種架構不匹配；智能反而必須分散至專門化的智能體之間，並在系統層級進行組織。我們將此稱為系統智能：即智能體系統將多個智慧組件組織與協調成一個連貫、具適應性的整體，以追求共同目標的能力。要實現系統智能，不僅僅是增加智能體；它還需要明確的結構來組織工作、協調異質智能體，並維護持續演化的執行狀態。我們提出圖工程（Graph Engineering），這是一個為下一代智能體系統而生的新興範式。與先前主要最佳化個別互動或智能體層級行為的範式不同，圖工程建構出明確、動態且持續演化的圖結構，用以表示任務、智能體與系統狀態。這些抽象化概念為組織複雜目標、編排異質智能體、系統動態建模，以及實現可擴展的智能體演化，提供了統一的基礎。我們系統性地回顧了圖工程應用於LLM智能體的原理、方法與應用。相關論文、開源資料與專案已收錄於 https://github.com/DEEP-JLU/Awesome-Graph-Engineering。

English

LLMs have evolved from language generators to autonomous agents capable of complex, long-horizon tasks. This evolution has produced paradigms including Prompt Engineering to elicit model capabilities, Context Engineering to manage information access, Harness Engineering to organize external tools and resources, and Loop Engineering to support continual reflection and self-improvement. Yet as tasks grow more complex, individual intelligence faces a fundamental limit: many tasks require heterogeneous expertise, interdependent subtasks, parallel execution, independent verification, and persistent state, exceeding any single agent's organizational capacity. Augmenting one agent's capabilities or context cannot resolve this architectural mismatch; intelligence must instead be distributed across specialized agents and organized at the system level. We call this System Intelligence: an agent system's ability to organize and coordinate multiple intelligent components into a coherent, adaptive whole pursuing a shared objective. Achieving it requires more than adding agents; it demands explicit structures to organize work, coordinate heterogeneous agents, and maintain evolving execution states. We introduce Graph Engineering, an emerging paradigm for next-generation agent systems. Unlike prior paradigms that mainly optimize individual interactions or agent-level behavior, Graph Engineering constructs explicit, dynamic, evolving graph structures representing tasks, agents, and system states. These abstractions provide a unified foundation for organizing complex objectives, orchestrating heterogeneous agents, modeling system dynamics, and enabling scalable agent evolution. We systematically review the principles, methodologies, and applications of Graph Engineering for LLM agents. Related papers, open-source data, and projects are collected at https://github.com/DEEP-JLU/Awesome-Graph-Engineering.