# GraphSkill: Documentation-Guided Hierarchical Retrieval-Augmented Coding for Complex Graph Reasoning

arXiv: https://arxiv.org/abs/2603.06620 · HTML: https://mlsanity.com/paper/2603.06620/

## Key facts

- Cited by 4 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 15 of its 49 references that are in the map.
- First posted on arXiv 20 Feb 2026.

## 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, 15 of 15)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Text and Code Embeddings by Contrastive Pre-Training](https://mlsanity.com/paper/2201.10005/) (2022)
- [Corrective Retrieval Augmented Generation](https://mlsanity.com/paper/2401.15884/) (2024)
- [Let Your Graph Do the Talking: Encoding Structured Data for LLMs](https://mlsanity.com/paper/2402.05862/) (2024)
- [GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability](https://mlsanity.com/paper/2403.04483/) (2024)
- [Agentic Retrieval-Augmented Generation for Time Series Analysis](https://mlsanity.com/paper/2408.14484/) (2024)
- [GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration](https://mlsanity.com/paper/2410.18032/) (2024)
- [Enhance Graph Alignment for Large Language Models](https://mlsanity.com/paper/2410.11370/) (2024)
- [CodeGraph: Enhancing Graph Reasoning of LLMs with Code](https://mlsanity.com/paper/2408.13863/) (2024)
- [MolX: Enhancing Large Language Models for Molecular Understanding With A Multi-Modal Extension](https://mlsanity.com/paper/2406.06777/) (2024)
- [Pseudocode-Injection Magic: Enabling LLMs to Tackle Graph Computational Tasks](https://mlsanity.com/paper/2501.13731/) (2025)
- [Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph](https://mlsanity.com/paper/2511.00086/) (2025)

## Built on by (most cited first, 4 of 4)

- [A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications](https://mlsanity.com/paper/2605.07358/) (2026)
- [Are Large Language Models Suitable for Graph Computation? Progress and Prospects](https://mlsanity.com/paper/2606.06865/) (2026)
- [Unified Multi-Dimensional Benchmark for Complex Graph Reasoning in Large Language Models](https://mlsanity.com/paper/2608.12391/) (2026)
- [Towards a Systems Foundation for Agentic Skills: Architecture, Lifecycle, and Security](https://mlsanity.com/paper/2608.29596/) (2026)

## Abstract (arXiv)

The growing demand for automated graph algorithm reasoning has attracted increasing attention in the large language model (LLM) community. Recent LLM-based graph reasoning methods typically decouple task descriptions from graph data, generate executable code augmented by retrieval from technical documentation, and refine the code through debugging. However, we identify two key limitations in existing approaches: (i) they treat technical documentation as flat text collections and ignore its hierarchical structure, leading to noisy retrieval that degrades code generation quality; and (ii) their debugging mechanisms focus primarily on runtime errors, yet ignore more critical logical errors. To address them, we propose method, an textitagentic hierarchical retrieval-augmented coding framework that exploits the document hierarchy through top-down traversal and early pruning, together with a textitself-debugging coding agent that iteratively refines code using automatically generated small-scale test cases. To enable comprehensive evaluation of complex graph reasoning, we introduce a new dataset, dataset, covering small-scale, large-scale, and composite graph reasoning tasks. Extensive experiments demonstrate that our method achieves higher task accuracy and lower inference cost compared to baselinesfootnoteThe code is available at hrefhttps://github.com/FairyFali/GraphSkilltextcolorbluehttps://github.com/FairyFali/GraphSkill..