# When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost

arXiv: https://arxiv.org/abs/2607.24010 · HTML: https://mlsanity.com/paper/2607.24010/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 27 Jul 2026.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 19 of 19)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting](https://mlsanity.com/paper/2507.02939/) (2025)
- [SafetyRepro: Configuration-Conditional Rank Instability on Alignment Benchmarks](https://mlsanity.com/paper/2605.25492/) (2026)
- [DSPC: Dual-Stage Progressive Compression Framework for Efficient Long-Context Reasoning](https://mlsanity.com/paper/2509.13723/) (2025)
- [The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents](https://mlsanity.com/paper/2605.08060/) (2026)
- [Beyond Accuracy: Measuring Bias Acknowledgment in Chain-of-Thought Reasoning for Responsible AI Evaluation](https://mlsanity.com/paper/2606.15127/) (2026)
- [Pre-Registering the Detectable Effect: A Paired-MDE Budget for 4-bit Quantization Benchmarks, with a Pilot Audit](https://mlsanity.com/paper/2605.28873/) (2026)
- [How Early Is Early Enough? Design-Dependent Observation-Window Sufficiency in Subscription Churn Prediction](https://mlsanity.com/paper/2607.00473/) (2026)
- [GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases](https://mlsanity.com/paper/2605.30237/) (2026)
- [Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting](https://mlsanity.com/paper/2606.18367/) (2026)
- [Class Weighting versus Amount Conditioning in Credit-Card Fraud Detection: A Dollar-Metric Study with a Temporal Explanation Audit](https://mlsanity.com/paper/2607.14686/) (2026)
- [Carbon-Aware Compute--Power Scheduling for AI Data Centers with Microgrid Prosumer Operations](https://mlsanity.com/paper/2605.03751/) (2026)
- [Optimality of Sequential Filtering Under Independent Cost and Selectivity Models](https://mlsanity.com/paper/2606.07589/) (2026)
- [Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite](https://mlsanity.com/paper/2606.11257/) (2026)

## Built on by (most cited first, 2 of 2)

- [Evidence-Unit Fairness and the Limits of Query-Adaptive Sparse-Dense Fusion in Financial Document Retrieval](https://mlsanity.com/paper/2608.00183/) (2026)
- [Beyond the Query: Do Retrieval Signals Improve Adaptive Multimodal RAG Routing?](https://mlsanity.com/paper/2609.12437/) (2026)

## Abstract (arXiv)

Active RAG systems decide when to retrieve external knowledge during generation, making them a budget-sensitive case of agentic RAG and self-adaptive retrieval. Yet evaluations often leave the operating point underspecified: two systems may both claim a 50% evidence-usage budget while realizing different held-out usage rates, so higher accuracy can reflect a looser budget rather than a better retrieval policy. We study budget-aware evaluation for Active RAG by recasting active retrieval as utility estimation, where retrieval is valuable only through its marginal correctness change over a no-retrieval answer. This view separates three questions that single-point evaluations conflate: whether trigger scores rank useful retrieval decisions, whether thresholds calibrated on past data meet future budgets, and how trigger-side computation changes deployment cost. We operationalize these questions with exact top-k utility frontiers, deployable threshold frontiers, conservative budget frontiers, harm audits, and cost decompositions. Across knowledge-intensive multi-hop QA datasets and open instruction models, retrieval harm is non-negligible, router rankings change across datasets and budgets, nominal thresholds can miss target usage, and simple uncertainty or retrieval-score baselines often rival learned utility routers. Budget-aware Active RAG evaluations should therefore report frontiers, realized usage, threshold-transfer error, harm rates, and cost decompositions alongside accuracy.