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

Source: https://huggingface.co/papers/2608.21156 Published on Aug 21

·

Submitted byhttps://huggingface.co/eric-xiang

ericon Aug 24

#2 Paper of the day Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Graph Engineering organizes multi-agent LLM systems through dynamic graph structures to coordinate specialized agents and manage complex, evolving tasks.

LLMs have evolved from language generators to autonomous agents capable of complex, long-horizon tasks. This evolution has produced paradigms includingPrompt Engineeringto elicit model capabilities,Context Engineeringto manage information access,Harness Engineeringto organize external tools and resources, andLoop Engineeringto 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 thisSystem 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 introduceGraph Engineering, an emerging paradigm for next-generation agent systems. Unlike prior paradigms that mainly optimize individual interactions or agent-level behavior,Graph Engineeringconstructs explicit, dynamic, evolvinggraph structuresrepresenting 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 ofGraph EngineeringforLLM agents. Related papers, open-source data, and projects are collected at https://github.com/DEEP-JLU/Awesome-Graph-Engineering.

View arXiv pageView PDFGitHub9Add to collection

Get this paper in your agent:

hf papers read 2608\.21156

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.21156 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.21156 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.21156 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.