# RAG robustness and adaptive retrieval

Area: [Retrieval-augmented generation](https://mlsanity.com/rag/index.md). HTML: https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/

## Key facts

- RAG robustness and adaptive retrieval: 589 papers on arXiv since 2021 (data through 14 Oct 2026).
- 199 of its 589 mapped papers (34%) cite “Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection” (2023, arXiv 2310.11511).
- 61 of its 589 mapped papers (10%) cite “Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity” (2024, arXiv 2403.14403).
- 16 new papers 17 Sep–14 Oct.

## Most cited here

- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023), cited by 199 papers here
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024), cited by 61 papers here
- [Benchmarking Large Language Models in Retrieval-Augmented Generation](https://mlsanity.com/paper/2309.01431/) (2023), cited by 42 papers here
- [Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models](https://mlsanity.com/paper/2402.14409/) (2024), cited by 29 papers here
- [Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training](https://mlsanity.com/paper/2405.20978/) (2024), cited by 27 papers here
- [InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales](https://mlsanity.com/paper/2406.13629/) (2024), cited by 22 papers here
- [Retrieval-Augmented Generation with Conflicting Evidence](https://mlsanity.com/paper/2504.13079/) (2025), cited by 19 papers here
- [RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation](https://mlsanity.com/paper/2404.00610/) (2024), cited by 17 papers here
- [ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence](https://mlsanity.com/paper/2404.10198/) (2024), cited by 17 papers here
- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024), cited by 17 papers here

## New (17 Sep–14 Oct)

- [RCER: Reconstructing Cross-Evidence Relations for Iterative Retrieval-Augmented Generation](https://mlsanity.com/paper/2610.19398/) (2026-10-14)
- [GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence Reports](https://mlsanity.com/paper/2610.12617/) (2026-10-08)
- [RAG-Stress: Probing the Limits of Evidence Reliance in Retrieval-Augmented Generation](https://mlsanity.com/paper/2610.11183/) (2026-10-08)
- [Finding the Right Balance: Relevance and Diversity in LLM Retrieval](https://mlsanity.com/paper/2610.09412/) (2026-10-07)
- [Tool-calling retrieval versus vector RAG for a small Greek--English knowledge base: accuracy and robustness to how users type Greek](https://mlsanity.com/paper/2610.08205/) (2026-10-06)
- [RAGStress: A controlled benchmark for evaluating retrieval-augmented generation under knowledge-base degradation](https://mlsanity.com/paper/2610.04691/) (2026-10-03)
- [Jev-as-a-Judge for RAG Claim Verification: Confidence-Gated Cascading Between a Non-Generative Verifier and a Frontier LLM](https://mlsanity.com/paper/2610.20634/) (2026-09-30)
- [Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering](https://mlsanity.com/paper/2609.38473/) (2026-09-29)
- [Byzantine-Robust Federated RAG via Aligned Calibration and Fixed-Membership Conformal Prediction](https://mlsanity.com/paper/2609.33037/) (2026-09-29)
- [Conformal Factuality Control for Multi-Hop Retrieval-Augmented Generation](https://mlsanity.com/paper/2609.38222/) (2026-09-27)
- [Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG](https://mlsanity.com/paper/2609.37469/) (2026-09-27)
- [Regime Boundary Alignment for Evidence-Gated Question Answering](https://mlsanity.com/paper/2609.37491/) (2026-09-25)
- [Stale-Document Poisoning: When Outdated Retrieval Overrides Correct Model Answers](https://mlsanity.com/paper/2609.31342/) (2026-09-25)
- [Parameters vs. Context: TRACE Fine-Tuning for Robust Retrieval-Augmented Generation](https://mlsanity.com/paper/2609.30337/) (2026-09-24)
- [To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech](https://mlsanity.com/paper/2609.30227/) (2026-09-24)
- [Bridging Static and Agentic RAG for Taiwanese Historical Question Answering](https://mlsanity.com/paper/2609.23056/) (2026-09-19)