mlsanityData to 7 Oct 2026

When Knowledge Is Not Free: Cost-Aware Evidence Selection in Retrieval-Augmented Generation

arXiv 2606.02245 ↗First posted 1 Jun 2026cs.CLcited by 3

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) typically assumes that external knowledge is free, but many high-quality sources are paywalled, licensed, restricted, or otherwise costly to access. We introduce cost-aware RAG, a setting where retrieved evidence is assigned access-cost tiers and systems must answer under an explicit evidence-access budget. We instantiate this setting by augmenting MS MARCO v2.1 with access-friction tiers and evaluate budgeted evidence selection across general-domain and domain-specific QA benchmarks. Our results show that static selection is brittle: no fixed selector uniformly dominates, and larger budgets do not reliably improve answer quality, even when costly evidence is domain-matched. We then study agentic cost-aware RAG, where an LLM decides when to retrieve, which tier to access, and when to stop. Agents show strong promise as adaptive evidence-acquisition controllers, but their behavior remains highly model- and task-dependent. These findings suggest that cost-aware evidence acquisition is a central challenge for the next generation of RAG systems. All code and data are available at https://github.com/Mignonmy/Cost-Aware.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 18 of its 22 references that are in the map. First posted on arXiv 1 Jun 2026.

Builds on

18 of 22 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity21 Mar
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 16

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  6. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  8. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  9. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324
  10. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  11. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
  12. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
4 more
  1. 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 326
  2. 2024TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Textcited by 60
  3. 2024DeepNote: Note-Centric Deep Retrieval-Augmented Generationcited by 8
  4. 2026Budget-Constrained Online Retrieval-Augmented Generation: The Chunk-as-a-Service Modelcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026FLOWREADER: Min-Cost Flow Optimization for Multi-Modal Long Document Q&Acited by 1
  2. 2026Modality Relevance is not Modality Utility: Post-hoc Selective Modality Escalation for Cost-Aware Multimodal RAGcited by 1
  3. 2026Engineering Reliable Commit Gates for Agentic AI: Cost-Aware Verification Portfolios under Common-Mode Data Failurescited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost
  2. 2025FAIR-RAG: Faithful Adaptive Iterative Refinement for Retrieval-Augmented Generation
  3. 2026MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation
  4. 2026Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
  5. 2026Assessing the Downstream Utility of Evidence-Aware Retrieval in RAG
  6. 2026BELIEFRAG: Making Adaptive RAG State-Aware under Evolving Evidence
  7. 2026SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation
  8. 2025Towards Transparent RAG: Fostering Evidence Traceability in LLM Generation via Reinforcement Learning