GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining
Not on the map. Why?
Abstract (arXiv)
Large Language Models (LLMs) face significant limitations when applied to large-scale graphs, struggling with context constraints and inflexible reasoning. We present GraphChain, a framework that enables LLMs to analyze complex graphs through dynamic sequences of specialized tools, mimicking human exploratory intelligence. Our approach introduces two key innovations: (1) Progressive Graph Distillation, a reinforcement learning mechanism that generates optimized tool sequences balancing task relevance with information compression, and (2) Structure-aware Test-Time Adaptation, which efficiently tailors tool selection strategies to diverse graph topologies using spectral properties and lightweight adapters without costly retraining. Experiments show GraphChain significantly outperforms prior methods, enabling scalable and adaptive LLM-driven graph analysis.
Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 62 of its 92 references that are in the map. First posted on arXiv 1 Nov 2025.
Builds on
62 of 92 references.
References · 62
- 2023GPT-4 Technical Reportcited by 18,396
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
- 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
- 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
- 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
- 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
- 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,121
- 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
- 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
38 more
- 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 382
- 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
- 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 328
- 2023Can Language Models Solve Graph Problems in Natural Language?cited by 252
- 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instructioncited by 248
- 2023GraphGPT: Graph Instruction Tuning for Large Language Modelscited by 226
- 2024Tool Learning with Large Language Models: A Surveycited by 223
- 2023Language is All a Graph Needscited by 220
- 2020Generalization and Representational Limits of Graph Neural Networkscited by 218
- 2023GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarkingcited by 210
- 2023TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIscited by 184
- 2024LLaGA: Large Language and Graph Assistantcited by 181
- 2022GreaseLM: Graph REASoning Enhanced Language Models for Question Answeringcited by 171
- 2019Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensicscited by 164
- 2025Dynamic Cheatsheet: Test-Time Learning with Adaptive Memorycited by 163
- 2022Learning on Large-scale Text-attributed Graphs via Variational Inferencecited by 155
- 2023TaskBench: Benchmarking Large Language Models for Task Automationcited by 144
- 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 135
- 2022A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Languagecited by 131
- 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Callscited by 124
- 2023On the Tool Manipulation Capability of Open-source Large Language Modelscited by 122
- 2023GraphText: Graph Reasoning in Text Spacecited by 111
- 2023GraphLLM: Boosting Graph Reasoning Ability of Large Language Modelcited by 107
- 2023Graph-ToolFormer: To Empower LLMs with Graph Reasoning Ability via Prompt Augmented by ChatGPTcited by 80
- 2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learningcited by 74
- 2024ToolGen: Unified Tool Retrieval and Calling via Generationcited by 74
- 2023Making Language Models Better Tool Learners with Execution Feedbackcited by 70
- 2019Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecastingcited by 69
- 2023Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculumcited by 65
- 2024LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddingscited by 61
- 2024ToolNet: Connecting Large Language Models with Massive Tools via Tool Graphcited by 60
- 2024InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignmentcited by 56
- 2024Efficient Tuning and Inference for Large Language Models on Textual Graphscited by 54
- 2024Can LLM Graph Reasoning Generalize beyond Pattern Memorization?cited by 47
- 2024HiGPT: Heterogeneous Graph Language Modelcited by 45
- 2023ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Modelscited by 43
- 2024Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environmentscited by 39
- 2023ToolCoder: Teach Code Generation Models to use API search toolscited by 37
50 most cited of 62 All 62 (JSON)
Built on by
Citing papers per year: 2026: 5.
5 papers.
- 2026GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Taskscited by 2
- 2026GraphSeek: Next-Generation Graph Analytics with LLMscited by 1
- 2026Clustering as Reasoning: A k-Means Interpretation of Chain-of-Thought Graph Learningcited by 1
- 2026LoReC: Rethinking Large Language Models for Graph Data Analysiscited by 0
- 2026Are Large Language Models Suitable for Graph Computation? Progress and Prospectscited by 0
- 2026GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks3 Aug 2026
- 2026Are Large Language Models Suitable for Graph Computation? Progress and Prospects5 Jun 2026
- 2026Clustering as Reasoning: A k-Means Interpretation of Chain-of-Thought Graph Learning24 May 2026
- 2026LoReC: Rethinking Large Language Models for Graph Data Analysis20 Apr 2026
- 2026GraphSeek: Next-Generation Graph Analytics with LLMs11 Feb 2026
Similar, not cited
Close in wording, no citation either way
- 2024GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability
- 2026Teaching LLMs to See Graphs: Unifying Text and Structural Reasoning
- 2025Exploring Graph Learning Tasks with Pure LLMs: A Comprehensive Benchmark and Investigation
- 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs
- 2024GraphArena: Evaluating and Exploring Large Language Models on Graph Computation
- 2025GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models
- 2024GUNDAM: Aligning Large Language Models with Graph Understanding
- 2025GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks