# RAG pipeline design and evaluation

Area: [Retrieval-augmented generation](https://mlsanity.com/rag/index.md). HTML: https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/

## Key facts

- RAG pipeline design and evaluation: 706 papers on arXiv since 2022 (data through 14 Oct 2026).
- 188 of its 706 mapped papers (27%) cite “Retrieval-Augmented Generation for Large Language Models: A Survey” (2023, arXiv 2312.10997).
- 69 of its 706 mapped papers (10%) cite “ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems” (2023, arXiv 2311.09476).
- 9 new papers 17 Sep–14 Oct.

## Most cited here

- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023), cited by 188 papers here
- [ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2311.09476/) (2023), cited by 69 papers here
- [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023), cited by 62 papers here
- [The Power of Noise: Redefining Retrieval for RAG Systems](https://mlsanity.com/paper/2401.14887/) (2024), cited by 52 papers here
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024), cited by 49 papers here
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024), cited by 46 papers here
- [MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries](https://mlsanity.com/paper/2401.15391/) (2024), cited by 42 papers here
- [Evaluation of Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2405.07437/) (2024), cited by 41 papers here
- [FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research](https://mlsanity.com/paper/2405.13576/) (2024), cited by 36 papers here
- [Seven Failure Points When Engineering a Retrieval Augmented Generation System](https://mlsanity.com/paper/2401.05856/) (2024), cited by 30 papers here

## New (17 Sep–14 Oct)

- [Analyzing performance of Retrieval Augmented Generation models for Question Answering Tasks](https://mlsanity.com/paper/2610.20419/) (2026-10-14)
- [Configuring RAG Systems: What Breaks, Where Originates, and How to Fix](https://mlsanity.com/paper/2610.18567/) (2026-10-13)
- [RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees](https://mlsanity.com/paper/2610.11370/) (2026-10-08)
- [From Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QA](https://mlsanity.com/paper/2610.09361/) (2026-10-07)
- [Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning](https://mlsanity.com/paper/2610.01936/) (2026-10-01)
- [AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation](https://mlsanity.com/paper/2610.01218/) (2026-10-01)
- [LLM-as-a-Judge for Low-Resource Languages: Adapting Ragas and Comparative Ranking for Romanian](https://mlsanity.com/paper/2610.00406/) (2026-09-30)
- [Page-Aware Retrieval-Augmented Generation for EvalLLM 2026: A Five-Variant Study on French PDFs](https://mlsanity.com/paper/2609.34776/) (2026-09-28)
- [Re:CAP - Auditing Retrieval Coverage in Production RAG Pipelines](https://mlsanity.com/paper/2609.24122/) (2026-09-21)