mlsanityData to 7 Oct 2026

When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach

arXiv 2510.08952 ↗First posted 10 Oct 2025cs.LGcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Text-attributed graphs (TAGs) have become a key form of graph-structured data in modern data management and analytics, combining structural relationships with rich textual semantics for diverse applications. However, the effectiveness of analytical models, particularly graph neural networks (GNNs), is highly sensitive to data quality. Our empirical analysis shows that both conventional and LLM-enhanced GNNs degrade notably under textual, structural, and label imperfections, underscoring TAG quality as a key bottleneck for reliable analytics. Existing studies have explored data-level optimization for TAGs, but most focus on specific degradation types and target a single aspect like structure or label, lacking a systematic and comprehensive perspective on data quality improvement. To address this gap, we propose LAGA (Large Language and Graph Agent), a unified multi-agent framework for comprehensive TAG quality optimization. LAGA formulates graph quality control as a data-centric process, integrating detection, planning, action, and evaluation agents into an automated loop. It holistically enhances textual, structural, and label aspects through coordinated multi-modal optimization. Extensive experiments on 5 datasets and 16 baselines across 9 scenarios demonstrate the effectiveness, robustness and scalability of LAGA, confirming the importance of data-centric quality optimization for reliable TAG analytics.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 31 of its 43 references that are in the map. First posted on arXiv 10 Oct 2025.

Builds on

31 of 43 references.

References · 31

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2017Graph Attention Networkscited by 8,854
  5. 2025Qwen3 Technical Reportcited by 8,195
  6. 2017Inductive Representation Learning on Large Graphscited by 6,284
  7. 2025Gemma 3 Technical Reportcited by 1,686
  8. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  9. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 253
  10. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 212
  11. 2023Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learningcited by 132
  12. 2022Towards Unsupervised Deep Graph Structure Learningcited by 112
19 more
  1. 2021NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphscited by 73
  2. 2024Efficient Tuning and Inference for Large Language Models on Textual Graphscited by 54
  3. 2024Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insightscited by 44
  4. 2023SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimizationcited by 35
  5. 2022LTE4G: Long-Tail Experts for Graph Neural Networkscited by 30
  6. 2023GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentationcited by 29
  7. 2022RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Networkcited by 27
  8. 2024Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?cited by 22
  9. 2021Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactionscited by 20
  10. 2022Compact Graph Structure Learning via Mutual Information Compressioncited by 20
  11. 2023GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classificationcited by 17
  12. 2024NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noisecited by 16
  13. 2019Denoising based Sequence-to-Sequence Pre-training for Text Generationcited by 15
  14. 2021GraphHop: An Enhanced Label Propagation Method for Node Classificationcited by 15
  15. 2022GraFN: Semi-Supervised Node Classification on Graph with Few Labels via Non-Parametric Distribution Assignmentcited by 10
  16. 2024Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Taskscited by 10
  17. 2019Contextual Text Denoising with Masked Language Modelscited by 8
  18. 2024IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph Learningcited by 6
  19. 2025Toward General and Robust LLM-enhanced Text-attributed Graph Learningcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments
  2. 2025Are LLMs Better GNN Helpers? Rethinking Robust Graph Learning under Deficiencies with Iterative Refinement
  3. 2025Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications
  4. 2026GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs
  5. 2025When Structure Doesn't Help: LLMs Do Not Read Text-Attributed Graphs as Effectively as We Expected
  6. 2025Lost in Serialization: Invariance and Generalization of LLM Graph Reasoners
  7. 2025Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detection
  8. 2026GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks