Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence

Large language models (LLMs) have rapidly evolved from language generation models into autonomous agents capable of solving increasingly complex and long-horizon tasks. This evolution has been accom- panied by a series of emerging engineering paradigms, including Prompt Engineering for eliciting model capabilities, Context Engineering for managing information access, Harness Engineering for organizing external tools and resources, and Loop Engineering for enabling continual reflection and self-improvement. However, as real-world tasks grow in complexity, a fundamental limitation of individual intelligence emerges: many tasks inherently require heterogeneous expertise, interdependent subtasks, parallel execution, independent verification, and persistent state, and these requirements exceed the organizational capacity of any single agent. Simply augmenting an individual agent’s capabilities or context cannot resolve this architectural mismatch. Instead, intelligence must be distributed across multiple specialized agents and organized at the system level. We refer to this capability as System Intelligence: the ability of an agent system to organize and coordinate multiple intelligent components into a coherent, adaptive whole that pursues a shared objective. Achieving System Intelligence, however, demands more than merely increasing the number of agents; it requires explicit structures for organizing work, coordinating heterogeneous agents, and maintaining evolving execution states. In this survey, we introduce Graph Engineering, an emerging paradigm for building next-generation agent systems. Unlike previous paradigms that primarily optimize individual interactions or agent-level behaviors, Graph Engineering focuses on constructing explicit, dynamic, and evolving graph structures that represent tasks, agents, and system states. Such graph-based abstractions provide a unified foundation for organizing complex objectives, orchestrating heterogeneous agents, modeling system dynamics, and enabling scalable agent evolution. In this paper, we systematically review the principles, methodologies, and applications of Graph Engineering in the era of LLM agents. All the related resources, including research papers, open-source data, and projects, are collected for the community at https://github.com/DEEP-JLU/Awesome-Graph-Engineering.