# CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval

arXiv: https://arxiv.org/abs/2606.28365 · HTML: https://mlsanity.com/paper/2606.28365/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 55 references that are in the map.
- First posted on arXiv 14 Jun 2026.

## Builds on (most cited first, 30 of 35)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models](https://mlsanity.com/paper/2405.14831/) (2024)
- [ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution](https://mlsanity.com/paper/2402.01145/) (2024)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [From RAG to Memory: Non-Parametric Continual Learning for Large Language Models](https://mlsanity.com/paper/2502.14802/) (2025)
- [BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2407.12883/) (2024)
- [Open Domain Question Answering over Tables via Dense Retrieval](https://mlsanity.com/paper/2103.12011/) (2021)
- [Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion](https://mlsanity.com/paper/2501.17887/) (2025)
- [TensorOpera Router: A Multi-Model Router for Efficient LLM Inference](https://mlsanity.com/paper/2408.12320/) (2024)
- [Optimizing Model Selection for Compound AI Systems](https://mlsanity.com/paper/2502.14815/) (2025)
- [Towards Optimizing the Costs of LLM Usage](https://mlsanity.com/paper/2402.01742/) (2024)
- [Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selection](https://mlsanity.com/paper/2405.02134/) (2024)
- [MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encodings](https://mlsanity.com/paper/2405.19504/) (2024)
- [KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG](https://mlsanity.com/paper/2502.09304/) (2025)
- [Multi-objective Asynchronous Successive Halving](https://mlsanity.com/paper/2106.12639/) (2021)
- [SiReRAG: Indexing Similar and Related Information for Multihop Reasoning](https://mlsanity.com/paper/2412.06206/) (2024)
- [WARP: An Efficient Engine for Multi-Vector Retrieval](https://mlsanity.com/paper/2501.17788/) (2025)
- [EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline](https://mlsanity.com/paper/2504.03598/) (2025)
- [Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems](https://mlsanity.com/paper/2502.18635/) (2025)
- [Multi-Objective Agentic Rewrites for Unstructured Data Processing](https://mlsanity.com/paper/2512.02289/) (2025)
- [Scaling Generative Verifiers For Natural Language Mathematical Proof Verification And Selection](https://mlsanity.com/paper/2511.13027/) (2025)
- [Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval](https://mlsanity.com/paper/2506.08074/) (2025)

## Abstract (arXiv)

RAG ingestion pipelines frequently augment search corpus index with semantic enrichment indices (e.g., synthetic queries or summaries generated from corpus chunks) that are subsequently queried alongside the base index to improve retrieval via better alignment between document representations and user intent. While these supplementary representations substantially improve retrieval quality, they introduce a computational bottleneck: the configuration space of enrichment types and generator models is combinatorial, and the cost of exhaustive index-time evaluation scales linearly with corpus size. We introduce CAMI (Cost-Aware Multi-Indexing), a framework that formalizes multi-index construction as a budgeted, multi-objective portfolio selection problem. CAMI targets the upstream decision of which enrichment views to generate and materialize before the retrieval backend is applied. CAMI incorporates three primary mechanisms: (i) an agentic discovery phase that proposes corpus-specific representation templates; (ii) an atomic-unit search procedure that evaluates individual enrichment-model pairs and recombines them via fidelity-local closure to identify synergistic portfolios; and (iii) a confidence-aware promotion schedule that prunes unpromising configurations early, decoupling optimization spend from total corpus size. We evaluate CAMI across diverse retrieval corpora. Our findings reveal that the framework systematically isolates high-recall portfolios under strict budget constraints, outperforming standard content-only baselines in challenging settings by up to 9.4% recall@10. Further, CAMI is able to systematically identify these high-recall portfolios using up to 5x less budget compared to random search baselines, making our approach practical in real production scenarios.