Awesome LLM RAG
A curated list of research papers, workshops, and tools on retrieval-augmented generation for large language models, organized by topic from embeddings to evaluation.
Awesome LLM RAG records advanced papers on retrieval-augmented generation (RAG) in large language models, organized into sections covering surveys and benchmarks, retrieval-enhanced LLMs, RAG instruction tuning, in-context learning, embeddings, simulators, search, long-text and memory, evaluation, optimization, application, and support for missing modalities.
Alongside the paper list, it links workshops and tutorials and a handful of related open-source projects, including agent orchestration tools, a desktop control panel for coding-agent ecosystems, and a chunking-strategy benchmarking tool for RAG.
Contributions are welcome as pull requests that add a paper's information to the relevant section.