GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs

• URL: http://arxiv.org/abs/2604.23626v1
• Date: Sun, 26 Apr 2026 09:38:32 GMT
• Title: GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs
• Abstract summary: GraphPlanner is a heterogeneous graph memory-augmented agentic router for multi-agent LLMs.<n>It generates routing for each query and supports both inductive and transductive inference.<n>GraphPlanner integrates historical memory and workflow memory into richer state representations.
• Score: 24.37693905714609
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM routing has achieved promising results in integrating the strengths of diverse models while balancing efficiency and performance. However, to support more realistic and challenging applications, routing must extend into agentic LLM settings, where task planning, multi-round cooperation among heterogeneous agents, and memory utilization are indispensable. To address this gap, we propose GraphPlanner, a heterogeneous graph memory-augmented agentic router for multi-agent LLMs that generates routing workflows for each query and supports both inductive and transductive inference. GraphPlanner formulates workflow generation as a Markov Decision Process (MDP), where at each step it selects both the LLM backbone and the agent role, including Planner, Executor, and Summarizer. By leveraging a heterogeneous graph, denoted as GARNet, to capture interaction memories among queries, agents, and responses, GraphPlanner integrates historical memory and workflow memory into richer state representations. The entire pipeline is optimized with reinforcement learning, jointly improving task-specific performance and computational efficiency. We evaluate GraphPlanner across 14 diverse LLM tasks and demonstrate that: (1) GraphPlanner outperforms strong single-round and multi-round routers, improving accuracy by up to 9.3% while reducing GPU cost from 186.26 GiB to 1.04 GiB; (2) GraphPlanner generalizes robustly to unseen tasks and LLMs, exhibiting strong zero-shot capabilities; and (3) GraphPlanner effectively leverages historical memories, supporting both inductive and transductive inference for more adaptive routing. Our code for GraphPlanner is released at https://github.com/ulab-uiuc/GraphPlanner.

Related papers

• Inference-Time Graph Engineering for Multi-Agent LLM Workflows [51.56038180639833]
  We introduce ReActNet, a training-free framework that compiles a query and a set of role-specialized agents into a sequence of directed communication graphs.<n>We show that ReActNet consistently improves over fixed-topology and learned-topology baselines while maintaining competitive inference cost.
  arXiv  Detail & Related papers  (2026-09-04T23:32:11Z)
• GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learning [20.75113227786218]
  Graph-based Agent Planning (GAP) is a novel framework that explicitly models inter-task dependencies through graph-based planning.<n>Our approach trains agent foundation models to decompose complex tasks into dependency-aware sub-task graphs.<n>This dependency-aware orchestration achieves substantial improvements in both execution efficiency and task accuracy.
  arXiv  Detail & Related papers  (2025-10-29T09:35:55Z)
• AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction [60.51319139563509]
  We introduce AutoGraph-R1, the first framework to directly optimize KG construction for task performance using Reinforcement Learning (RL)<n>We design two novel, task-aware reward functions, one for graphs as knowledge carriers and another as knowledge indices.<n>Our work shows it is possible to close the loop between construction and application, shifting the paradigm from building intrinsically good'' graphs to building demonstrably useful'' ones.
  arXiv  Detail & Related papers  (2025-10-17T06:03:36Z)
• GraphCogent: Mitigating LLMs' Working Memory Constraints via Multi-Agent Collaboration in Complex Graph Understanding [13.356521655409422]
  Large language models (LLMs) show promising performance on small-scale graph reasoning tasks but fail when handling real-world graphs with complex queries.<n>We propose GraphCogent, a collaborative agent framework that decomposes graph reasoning into specialized cognitive processes: sense, buffer, and execute.
  arXiv  Detail & Related papers  (2025-08-17T14:28:38Z)
• Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects [57.53024716739594]
  Graph-augmented LLM Agents (GLA) enhance structure, continuity, and coordination in complex agent systems.<n>This paper offers a timely and comprehensive overview of recent advances and highlights key directions for future work.<n>We hope this paper can serve as a roadmap for future research on GLA and foster a deeper understanding of the role of graphs in GLA agent systems.
  arXiv  Detail & Related papers  (2025-07-29T00:27:12Z)
• Plan-over-Graph: Towards Parallelable LLM Agent Schedule [53.834646147919436]
  Large Language Models (LLMs) have demonstrated exceptional abilities in reasoning for task planning.<n>This paper introduces a novel paradigm, plan-over-graph, in which the model first decomposes a real-life textual task into executable subtasks and constructs an abstract task graph.<n>The model then understands this task graph as input and generates a plan for parallel execution.
  arXiv  Detail & Related papers  (2025-02-20T13:47:51Z)
• GraphRouter: A Graph-based Router for LLM Selections [13.463815950807874]
  We introduce a novel inductive graph framework, named as Graph, to enhance the selection of Large Language Models (LLMs)<n>Through an edge prediction mechanism, Graph is able to predict attributes (the effect and cost of LLM response) of potential edges, allowing for optimized recommendations.<n>In experiments, Graph substantially surpasses existing routers, delivering a minimum performance improvement of 12.3%.
  arXiv  Detail & Related papers  (2024-10-04T18:02:48Z)
• Language Agents as Optimizable Graphs [31.220547147952278]
  We describe Large Language Models (LLMs)-based agents as computational graphs. Our framework can be used to efficiently develop, integrate, and automatically improve various LLM agents.
  arXiv  Detail & Related papers  (2024-02-26T18:48:27Z)
• LLaGA: Large Language and Graph Assistant [73.71990472543027]
  Large Language and Graph Assistant (LLaGA) is an innovative model to handle the complexities of graph-structured data. LLaGA excels in versatility, generalizability and interpretability, allowing it to perform consistently well across different datasets and tasks. Our experiments show that LLaGA delivers outstanding performance across four datasets and three tasks using one single model.
  arXiv  Detail & Related papers  (2024-02-13T02:03:26Z)
• Integrating Graphs with Large Language Models: Methods and Prospects [68.37584693537555]
  Large language models (LLMs) have emerged as frontrunners, showcasing unparalleled prowess in diverse applications. Merging the capabilities of LLMs with graph-structured data has been a topic of keen interest. This paper bifurcates such integrations into two predominant categories.
  arXiv  Detail & Related papers  (2023-10-09T07:59:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.