cs.AINov 4, 2026

Graph-Mediated Large Language Model Systems in the Agentic Era: Reasoning, Knowledge, Retrieval, Execution, and Coordination

Authors: Haihui Liu, Yang Chen, Zice Qiu, Yun Zhang, Jialun Zhong, Wenhua Wang, Yanzeng Li, Tian Wang

Organizations: Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai 519087, China · School of Geospatial Engineering and Science, Sun Yat-sen University, Zhuhai 519082, China · Faculty of Science and Technology, Beijing Normal-Hong Kong Baptist University, Zhuhai 519087, China · Wangxuan Institute of Computer Technology, Peking University, Beijing 100871, China · 

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.

Figures & tables

Explore similar work

CardsList
  1. Are Large Language Models Suitable for Graph Computation? Progress and Prospects

    Jun 5, 2026Yuting Zhang, Yi Han, Kai Wang +3LLM Reasoning with GraphsLLM Tool Use

  2. Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval

    Apr 17, 2026Hamed Jelodar, Samita Bai, Mohammad Meymani +3LLM Reasoning with GraphsGraph Retrieval-Augmented Generation

  3. LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems

    Jun 10, 2026Arijit Khan, Longxu Sun, Xin HuangKnowledge Augmentation for Language ModelsLLM Reasoning with Graphs