mlsanityData to 7 Oct 2026

Stop-RAG: Value-Based Retrieval Control for Iterative RAG

arXiv 2510.14337 ↗First posted 16 Oct 2025cs.LG cs.AIcited by 13

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

Abstract (arXiv)

Iterative retrieval-augmented generation (RAG) enables large language models to answer complex multi-hop questions, but each additional loop increases latency, costs, and the risk of introducing distracting evidence, motivating the need for an efficient stopping strategy. Existing methods either use a predetermined number of iterations or rely on confidence proxies that poorly reflect whether more retrieval will actually help. We cast iterative RAG as a finite-horizon Markov decision process and introduce Stop-RAG, a value-based controller that adaptively decides when to stop retrieving. Trained with full-width forward-view Q(λ) targets from complete trajectories, Stop-RAG learns effective stopping policies while remaining compatible with black-box APIs and existing pipelines. On multi-hop question-answering benchmarks, Stop-RAG consistently outperforms both fixed-iteration baselines and prompting-based stopping with LLMs. These results highlight adaptive stopping as a key missing component in current agentic systems, and demonstrate that value-based control can improve the accuracy of RAG systems.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 40 of its 50 references that are in the map. First posted on arXiv 16 Oct 2025.

Builds on

40 of 50 references.

References · 40

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  8. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  9. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  10. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  11. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  12. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
28 more
  1. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  2. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
  3. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  4. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  5. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  6. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  7. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  8. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  9. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  10. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
  11. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  12. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  13. 2023Active Retrieval Augmented Generationcited by 506
  14. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  15. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Modelscited by 423
  16. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  17. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  18. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 167
  19. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 146
  20. 2025Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learningcited by 107
  21. 2024Gecko: Versatile Text Embeddings Distilled from Large Language Modelscited by 81
  22. 2023Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrievalcited by 77
  23. 2024Inference Scaling for Long-Context Retrieval Augmented Generationcited by 65
  24. 2024DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Modelscited by 63
  25. 2024When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentationcited by 59
  26. 2025RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agentscited by 56
  27. 2025Chain-of-Retrieval Augmented Generationcited by 48
  28. 2024Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrievalcited by 28

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 13.

13 papers.

Sort:

By area:

  1. 2026Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trendscited by 8
  2. 2026TASR: Training-Free Adaptive Stopping for Iterative Retrievalcited by 4
  3. 2026Stop When Memory Suffices: Evidence-Conditioned Progressive Execution for LLM Agentscited by 2
  4. 2026HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agentscited by 2
  5. 2026EarlyEval: Cheaper Agent Evaluation via Early Outcome Predictioncited by 2
  6. 2026When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answeringcited by 1
  7. 2026SAGE: SLO-Aware Adaptive Retrieval for Production RAG Systemscited by 1
  8. 2026When Deep Research Agents Stagnate: Enhancing Reasoning with Retrieval-Aware Agent Controlcited by 1
  9. 2026Predicting Partial Answer Quality and Utility in Agentic Retrieval-Augmented Generationcited by 1
  10. 2026CoVeR: Coverage-Based Routing of Verifier Calls in Agentic Retrievalcited by 1
  11. 2026StateRAG: Typed State Contracts for Complex Retrieval-Augmented Generationcited by 0
  12. 2026Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAGcited by 0
1 more
  1. 2026What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025SIRAG: Towards Stable and Interpretable RAG with A Process-Supervised Multi-Agent Framework
  2. 2026SPARC-RAG: Adaptive Sequential-Parallel Scaling with Context Management for Retrieval-Augmented Generation
  3. 2026Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model
  4. 2025REAP: Enhancing RAG with Recursive Evaluation and Adaptive Planning for Multi-Hop Question Answering
  5. 2025MAO-ARAG: Multi-Agent Orchestration for Adaptive Retrieval-Augmented Generation
  6. 2025Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generation
  7. 2026PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering
  8. 2025Multi-hop Reasoning via Early Knowledge Alignment