mlsanityData to 14 Oct 2026

Incremental Retrieval-Augmented Generation for Human-in-the-Loop Decision Support

arXiv 2610.12666 ↗First posted 8 Oct 2026cs.HC cs.AIcited by 0

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

Abstract (arXiv)

We introduce iRAG, a human-in-the-loop decision-support system combining Retrieval-Augmented Generation (RAG) with Hybrid Decision-Making. Unlike conventional RAG systems, relying on static Knowledge Bases (KBs), our proposal addresses settings where the KB is initially empty and is progressively populated through human decisions. The system stores previous decisions as retrievable precedents and moves from silent observation to evidence-grounded contestation and, finally, to autonomous handling with abstention. Against an independent baseline, iRAG matches final-decision error under 10% drift without retrieval decay and reduces it under 40% drift across all configurations. Retrieval decay improves performance on changed knowledge while increasing error on stable knowledge, evidencing a stability--plasticity trade-off rather than a general advantage. Human oversight is an architectural provision of the workflow; its usability with real human users remains to be evaluated.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 21 of its 30 references that are in the map. First posted on arXiv 8 Oct 2026.

Builds on

21 of 30 references.

References · 21

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  4. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  5. 2023Active Retrieval Augmented Generationcited by 516
  6. 2020Learning under Concept Drift: A Reviewcited by 477
  7. 2020Consistent Estimators for Learning to Defer to an Expertcited by 271
  8. 2017Predict Responsibly: Improving Fairness and Accuracy by Learning to Defercited by 233
  9. 2021PAQ: 65 Million Probably-Asked Questions and What You Can Do With Themcited by 200
  10. 2024Corrective Retrieval Augmented Generationcited by 197
  11. 2024Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Modelscited by 76
  12. 2022Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensemblescited by 60
9 more
  1. 2023On the Stability-Plasticity Dilemma of Class-Incremental Learningcited by 56
  2. 2021Interactive Label Cleaning with Example-based Explanationscited by 49
  3. 2024Learning to Defer to a Population: A Meta-Learning Approachcited by 27
  4. 2021Incorporating Uncertainty in Learning to Defer Algorithms for Safe Computer-Aided Diagnosiscited by 17
  5. 2020Learning in the Wild with Incremental Skeptical Gaussian Processescited by 13
  6. 2025RAG Meets Temporal Graphs: Time-Sensitive Modeling and Retrieval for Evolving Knowledgecited by 13
  7. 2024Learning To Guide Human Decision Makers With Vision-Language Modelscited by 4
  8. 2024Bridging the Gap in Hybrid Decision-Making Systemscited by 1
  9. 2025A Frank System for Co-Evolutionary Hybrid Decision-Makingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
  2. 2025RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided Reasoning
  3. 2026The RAT: A Unified Bayesian Model for RAG Evaluation
  4. 2026Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning
  5. 2025Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalization
  6. 2024Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models
  7. 2025Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control
  8. 2026Enhancing LLMs through human feedback: a journey towards self-improvement