arXiv cs.AI· Haihui Liu, Yang Chen, Zice Qiu, Yun Zhang, Jialun Zhong, Wenhua Wang, Yanzeng Li, Tian Wang·· 2 小时前AI 评分38
智能体时代图中介导的 LLM 系统综述：推理、知识、检索、执行与协调
Graph-Mediated Large Language Model Systems in the Agentic Era: Reasoning, Knowledge, Retrieval, Execution, and Coordination
AI 导读
arXiv 一篇综述提出操作级“角色-位置”分类法，梳理图机制在大语言模型系统中对结构推理、知识锚定、检索与记忆的支持，以及图在组织执行依赖和多智能体通信中的作用。文章比较图观察与外部计算如何引导决策、记忆表示如何支持后续任务，并给出涵盖 benchmark、过程诊断与系统成本的评估框架，还指出自适应计算与停止、记忆维护、依赖感知恢复等开放挑战。
正文 · 原文
Abstract:Graphs play an increasingly important role in large language model (LLM) systems, supporting structural reasoning, knowledge grounding, retrieval, and memory. As these systems evolve toward the agentic era, graphs also organize execution dependencies and multi-agent communication, linking intermediate observations and retained information to subsequent decisions. However, understanding their contribution requires distinguishing the function of each graph operation, the component responsible for its computation, and the subsequent use of its output. This survey introduces an operation-level role--locus taxonomy for reasoning, knowledge and evidence, retrieval and memory, execution, and coordination. We compare how graph observations and external computations guide decisions, how memory representations and updates support later tasks, and how dependencies constrain execution and information delivery. These comparisons distinguish improvements in local metrics from downstream task performance while retaining the conditions under which results were reported. We then organize benchmarks, comparison designs, process diagnostics, and system costs into an evaluation framework. Finally, we identify open challenges in adaptive computation and stopping, memory maintenance, and dependency-aware recovery. The survey provides a basis for assessing when graph mechanisms are useful and for evaluating their effects across components and stages.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.05953 [cs.AI] |
| (or arXiv:2611.05953v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05953 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haihui Liu [view email]
[v1]
Wed, 4 Nov 2026 04:47:38 UTC (7,301 KB)
来源：arXiv cs.AI · arxiv.org