A field guide to the GraphRAG paper explosion

What it does

This repository is a curated reading list for graph-based retrieval-augmented generation, organized around the taxonomy from the maintainers’ own survey paper. It catalogs papers, benchmarks, and open-source projects into categories like Knowledge Organization, Knowledge Retrieval, and Knowledge Integration. Think of it as a card catalog for a subfield that is accumulating papers faster than most people can read abstracts.

The interesting bit

Instead of dumping links alphabetically, the list imposes a conceptual framework: it separates graphs used for indexing from graphs used as knowledge carriers, then breaks retrieval into semantic, logical, LLM-based, and GNN-based strategies. That structure makes it useful even if you already know the field—you can see exactly where a new paper fits.

Key highlights

• Anchored to the arXiv survey A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models
• Splits the literature into knowledge organization, retrieval mechanisms, and integration methods (fine-tuning and in-context learning)
• Includes dedicated sections for benchmarks and open-source projects
• Actively maintained with news updates on the authors’ own related work (LinearRAG, ProbeRAG, etc.)
• Accepts community contributions via pull requests

Verdict

Worth bookmarking if you are doing literature reviews or trying to navigate the GraphRAG paper deluge. Skip it if you are looking for a drop-in library—this is a card catalog, not a codebase.