GraphCogent: Mitigating LLMs' Working Memory Constraints via Multi-Agent Collaboration in Complex Graph Understanding

• URL: http://arxiv.org/abs/2508.12379v2
• Date: Tue, 30 Sep 2025 14:56:50 GMT
• Title: GraphCogent: Mitigating LLMs' Working Memory Constraints via Multi-Agent Collaboration in Complex Graph Understanding
• Authors: Rongzheng Wang, Shuang Liang, Qizhi Chen, Yihong Huang, Muquan Li, Yizhuo Ma, Dongyang Zhang, Ke Qin, Man-Fai Leung,
• Abstract summary: 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.
• Score: 13.356521655409422
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) show promising performance on small-scale graph reasoning tasks but fail when handling real-world graphs with complex queries. This phenomenon arises from LLMs' working memory constraints, which result in their inability to retain long-range graph topology over extended contexts while sustaining coherent multi-step reasoning. However, real-world graphs are often structurally complex, such as Web, Transportation, Social, and Citation networks. To address these limitations, we propose GraphCogent, a collaborative agent framework inspired by human Working Memory Model that decomposes graph reasoning into specialized cognitive processes: sense, buffer, and execute. The framework consists of three modules: Sensory Module standardizes diverse graph text representations via subgraph sampling, Buffer Module integrates and indexes graph data across multiple formats, and Execution Module combines tool calling and tool creation for efficient reasoning. We also introduce Graph4real, a comprehensive benchmark that contains four domains of real-world graphs (Web, Transportation, Social, and Citation) to evaluate LLMs' graph reasoning capabilities. Our Graph4real covers 21 different graph reasoning tasks, categorized into three types (Structural Querying, Algorithmic Reasoning, and Predictive Modeling tasks), with graph scales up to 10 times larger than existing benchmarks. Experiments show that Llama3.1-8B based GraphCogent achieves a 50% improvement over massive-scale LLMs like DeepSeek-R1 (671B). Compared to state-of-the-art agent-based baseline, our framework outperforms by 20% in accuracy while reducing token usage by 80% for in-toolset tasks and 30% for out-toolset tasks. Code will be available after review.

Related papers

• GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning [46.699075133532595]
  Recent Graph-based Retrieval-Augmented Generation (GraphRAG) methods introduce iterative interaction between knowledge graphs and large language models (LLMs) to enhance reasoning capability.<n>We propose GraphScout, a training-centric agentic graph reasoning framework equipped with more flexible graph exploration tools.
  arXiv  Detail & Related papers  (2026-03-02T03:25:40Z)
• G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning [58.73279333365234]
  Reinforcement Learning (RL) on synthetic graph-theoretic tasks can significantly scale graph reasoning abilities.<n>With RL on Erdos, G1 obtains substantial improvements in graph reasoning, where our finetuned 3B model even outperforms Qwen2.5-72B-Instruct (24x size)<n>Our findings offer an efficient, scalable path for building strong graph reasoners by finetuning LLMs with RL on graph-theoretic tasks.
  arXiv  Detail & Related papers  (2025-05-24T04:33:41Z)
• An Automatic Graph Construction Framework based on Large Language Models for Recommendation [49.51799417575638]
  We introduce AutoGraph, an automatic graph construction framework based on large language models for recommendation.<n>LLMs infer the user preference and item knowledge, which is encoded as semantic vectors.<n>Latent factors are incorporated as extra nodes to link the user/item nodes, resulting in a graph with in-depth global-view semantics.
  arXiv  Detail & Related papers  (2024-12-24T07:51:29Z)
• Scalable and Accurate Graph Reasoning with LLM-based Multi-Agents [27.4884498301785]
  We introduce GraphAgent-Reasoner, a fine-tuning-free framework for explicit and precise graph reasoning. Inspired by distributed graph computation theory, our framework decomposes graph problems into smaller, node-centric tasks that are distributed among multiple agents. Our framework demonstrates the capability to handle real-world graph reasoning applications such as webpage importance analysis.
  arXiv  Detail & Related papers  (2024-10-07T15:34:14Z)
• Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models [88.4320775961431]
  We introduce ProGraph, a benchmark for large language models (LLMs) to process graphs.<n>Our findings reveal that the performance of current LLMs is unsatisfactory, with the best model achieving only 36% accuracy.<n>We propose LLM4Graph datasets, which include crawled documents and auto-generated codes based on 6 widely used graph libraries.
  arXiv  Detail & Related papers  (2024-09-29T11:38:45Z)
• GraphStorm: all-in-one graph machine learning framework for industry applications [75.23076561638348]
  GraphStorm is an end-to-end solution for scalable graph construction, graph model training and inference. Every component in GraphStorm can operate on graphs with billions of nodes and can scale model training and inference to different hardware without changing any code. GraphStorm has been used and deployed for over a dozen billion-scale industry applications after its release in May 2023.
  arXiv  Detail & Related papers  (2024-06-10T04:56:16Z)
• Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs [60.71360240206726]
  Large language models (LLMs) suffer from hallucinations, especially on knowledge-intensive tasks. Existing works propose to augment LLMs with individual text units retrieved from external knowledge corpora. We propose a framework called Graph Chain-of-thought (Graph-CoT) to augment LLMs with graphs by encouraging LLMs to reason on the graph iteratively.
  arXiv  Detail & Related papers  (2024-04-10T15:41:53Z)
• MGNet: Learning Correspondences via Multiple Graphs [78.0117352211091]
  Learning correspondences aims to find correct correspondences from the initial correspondence set with an uneven correspondence distribution and a low inlier rate. Recent advances usually use graph neural networks (GNNs) to build a single type of graph or stack local graphs into the global one to complete the task. We propose MGNet to effectively combine multiple complementary graphs.
  arXiv  Detail & Related papers  (2024-01-10T07:58:44Z)
• Talk like a Graph: Encoding Graphs for Large Language Models [15.652881653332194]
  We study the first comprehensive study of encoding graph-structured data as text for consumption by large language models (LLMs) We show that LLM performance on graph reasoning tasks varies on three fundamental levels: (1) the graph encoding method, (2) the nature of the graph task itself, and (3) interestingly, the very structure of the graph considered.
  arXiv  Detail & Related papers  (2023-10-06T19:55:21Z)

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.