# GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments

arXiv: https://arxiv.org/abs/2504.00711 · HTML: https://mlsanity.com/paper/2504.00711/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 39 of its 68 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 30 of 39)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Benchmarking Graph Neural Networks](https://mlsanity.com/paper/2003.00982/) (2020)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [GPT-GNN: Generative Pre-Training of Graph Neural Networks](https://mlsanity.com/paper/2006.15437/) (2020)
- [Data Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2006.06830/) (2020)
- [Sources of Hallucination by Large Language Models on Inference Tasks](https://mlsanity.com/paper/2305.14552/) (2023)
- [GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks](https://mlsanity.com/paper/2103.08826/) (2021)
- [G-Mixup: Graph Data Augmentation for Graph Classification](https://mlsanity.com/paper/2202.07179/) (2022)
- [Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps](https://mlsanity.com/paper/2407.07071/) (2024)
- [Data Augmentation for Deep Graph Learning: A Survey](https://mlsanity.com/paper/2202.08235/) (2022)
- [Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning](https://mlsanity.com/paper/2305.19523/) (2023)
- [Graph Foundation Models: Concepts, Opportunities and Challenges](https://mlsanity.com/paper/2310.11829/) (2023)
- [Knowledge Graph Reasoning with Relational Digraph](https://mlsanity.com/paper/2108.06040/) (2021)
- [A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models](https://mlsanity.com/paper/2501.13958/) (2025)
- [Position: Graph Foundation Models are Already Here](https://mlsanity.com/paper/2402.02216/) (2024)
- [Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering](https://mlsanity.com/paper/2404.14741/) (2024)
- [GraphEdit: Large Language Models for Graph Structure Learning](https://mlsanity.com/paper/2402.15183/) (2024)
- [AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning](https://mlsanity.com/paper/2205.15319/) (2022)
- [Emerging Drug Interaction Prediction Enabled by Flow-based Graph Neural Network with Biomedical Network](https://mlsanity.com/paper/2311.09261/) (2023)
- [Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs](https://mlsanity.com/paper/2310.09872/) (2023)
- [Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?](https://mlsanity.com/paper/2408.08685/) (2024)

## Built on by (most cited first, 19 of 19)

- [Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2505.23352/) (2025)
- [Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities](https://mlsanity.com/paper/2506.18019/) (2025)
- [RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction](https://mlsanity.com/paper/2601.06966/) (2026)
- [Model Unlearning via Sparse Autoencoder Subspace Guided Projections](https://mlsanity.com/paper/2505.24428/) (2025)
- [Octopus: Agentic Multimodal Reasoning with Six-Capability Orchestration](https://mlsanity.com/paper/2511.15351/) (2025)
- [GraphOracle: Efficient Fully-Inductive Knowledge Graph Reasoning via Relation-Dependency Graphs](https://mlsanity.com/paper/2505.11125/) (2025)
- [Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization](https://mlsanity.com/paper/2505.00812/) (2025)
- [Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications](https://mlsanity.com/paper/2510.21131/) (2025)
- [VideoSeg-R1:Reasoning Video Object Segmentation via Reinforcement Learning](https://mlsanity.com/paper/2511.16077/) (2025)
- [A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data](https://mlsanity.com/paper/2601.17717/) (2026)
- [Mixture of Length and Pruning Experts for Knowledge Graphs Reasoning](https://mlsanity.com/paper/2507.20498/) (2025)
- [LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger](https://mlsanity.com/paper/2607.28374/) (2026)
- [MLDebugging: Towards Benchmarking Code Debugging Across Multi-Library Scenarios](https://mlsanity.com/paper/2506.13824/) (2025)
- [SnapBench: Benchmarking Snap-and-Ask Multimodal Retrieval for Mobile Interactions](https://mlsanity.com/paper/2608.29607/) (2026)
- [ScEdit: Script-based Assessment of Knowledge Editing](https://mlsanity.com/paper/2505.23291/) (2025)
- [Multi-Agent Agentic Graph Learning via Structural Signatures](https://mlsanity.com/paper/2609.09565/) (2026)
- [Can LLM Agents Simulate Dynamic Networks? A Case Study on Email Networks with Phishing Synthesis](https://mlsanity.com/paper/2605.12507/) (2026)
- [LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluation](https://mlsanity.com/paper/2609.33521/) (2026)
- [No-Free-Graph: Learning When Multimodal Data Should Be Graphified](https://mlsanity.com/paper/2610.02768/) (2026)

## Abstract (arXiv)

The era of foundation models has revolutionized AI research, yet Graph Foundation Models (GFMs) remain constrained by the scarcity of large-scale graph corpora. Traditional graph data synthesis techniques primarily focus on simplistic structural operations, lacking the capacity to generate semantically rich nodes with meaningful textual attributes: a critical limitation for real-world applications. While large language models (LLMs) demonstrate exceptional text generation capabilities, their direct application to graph synthesis is impeded by context window limitations, hallucination phenomena, and structural consistency challenges. To address these issues, we introduce GraphMaster, the first multi-agent framework specifically designed for graph data synthesis in data-limited environments. GraphMaster orchestrates four specialized LLM agents (Manager, Perception, Enhancement, and Evaluation) that collaboratively optimize the synthesis process through iterative refinement, ensuring both semantic coherence and structural integrity. To rigorously evaluate our approach, we create new data-limited "Sub" variants of six standard graph benchmarks, specifically designed to test synthesis capabilities under realistic constraints. Additionally, we develop a novel interpretability assessment framework that combines human evaluation with a principled Grassmannian manifold-based analysis, providing both qualitative and quantitative measures of semantic coherence. Experimental results demonstrate that GraphMaster significantly outperforms traditional synthesis methods across multiple datasets, establishing a strong foundation for advancing GFMs in data-scarce environments.