# Are Large Language Models In-Context Graph Learners?

arXiv: https://arxiv.org/abs/2502.13562 · HTML: https://mlsanity.com/paper/2502.13562/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 4 of its 58 references that are in the map.
- First posted on arXiv 19 Feb 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- Retrieval-augmented generation / [Knowledge-graph and structured-knowledge RAG](https://mlsanity.com/rag/knowledge-graph-and-structured-knowledge-rag/)

## Builds on (most cited first, 4 of 4)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [A Survey of Adversarial Learning on Graphs](https://mlsanity.com/paper/2003.05730/) (2020)

## Built on by (most cited first, 12 of 12)

- [Graph is a Substrate Across Data Modalities](https://mlsanity.com/paper/2601.22384/) (2026)
- [Are Large Language Models Good Temporal Graph Learners?](https://mlsanity.com/paper/2506.05393/) (2025)
- [Higher-Order Knowledge Representations for Agentic Scientific Reasoning](https://mlsanity.com/paper/2601.04878/) (2026)
- [Node-as-Agent: Graph Agentic Network](https://mlsanity.com/paper/2508.00429/) (2025)
- [Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning](https://mlsanity.com/paper/2509.00975/) (2025)
- [GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models](https://mlsanity.com/paper/2511.07457/) (2025)
- [Colorful Talks with Graphs: Human-Interpretable Graph Encodings for Large Language Models](https://mlsanity.com/paper/2602.10386/) (2026)
- [Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models](https://mlsanity.com/paper/2603.02938/) (2026)
- [Riemannian Geometry Speaks Louder Than Words: From Graph Foundation Model to Next-Generation Graph Intelligence](https://mlsanity.com/paper/2603.21601/) (2026)
- [Rethinking Efficient Graph Coarsening via a Non-Selfishness Principle](https://mlsanity.com/paper/2605.13021/) (2026)
- [Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression](https://mlsanity.com/paper/2601.08187/) (2026)
- [Training Graph Foundation Models on The Web Graph](https://mlsanity.com/paper/2609.30894/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable in-context reasoning capabilities across a wide range of tasks, particularly with unstructured inputs such as language or images. However, LLMs struggle to handle structured data, such as graphs, due to their lack of understanding of non-Euclidean structures. As a result, without additional fine-tuning, their performance significantly lags behind that of graph neural networks (GNNs) in graph learning tasks. In this paper, we show that learning on graph data can be conceptualized as a retrieval-augmented generation (RAG) process, where specific instances (e.g., nodes or edges) act as queries, and the graph itself serves as the retrieved context. Building on this insight, we propose a series of RAG frameworks to enhance the in-context learning capabilities of LLMs for graph learning tasks. Comprehensive evaluations demonstrate that our proposed RAG frameworks significantly improve LLM performance on graph-based tasks, particularly in scenarios where a pretrained LLM must be used without modification or accessed via an API.