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

• URL: http://arxiv.org/abs/2606.28365v1
• Date: Sun, 14 Jun 2026 16:59:18 GMT
• Title: CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval
• Abstract summary: CAMI (Cost-Aware Multi-Indexing) is a framework that formalizes multi-index construction as a budgeted, multi-objective portfolio selection problem.<n>Our findings reveal that the framework systematically isolates high-recall portfolios under strict budget constraints.<n> CAMI is able to systematically identify these high-recall portfolios using up to 5x less budget compared to random search baselines.
• Score: 7.07006462273528
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Agent-UCT: Upper Confidence Bounds Applied to Trees for Agentic Workflow Optimization with Cost-Awareness [11.231092673447735]
  We introduce Agent-based Cost-Aware Upper Bounds Applied to Trees, a tree search algorithm that extends UCT with a reuse-aware regularization term derived from a bipartite prefix reuse graph.<n>Agent-UCT biases selection toward branches that leverage previously materialized configuration prefixes, reducing redundant execution while maintaining effective exploration.<n>WTB (Workflow Test Bench) provides deterministic replay, content-addressable caching, and transactional consistency, ensuring that intermediate states are materialized once and reused across the search computation.
  arXiv  Detail & Related papers  (2026-07-27T08:41:18Z)
• Beyond Fixed Depths and Widths: Optimizing Textual Decoding Tries in LLM-based Generative Recommendation [59.20704286413859]
  We propose a novel framework that co-designs textual term IDs and their underlying decoding trie.<n> BONSAI achieves up to a 21.6% relative improvement over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-07-18T04:31:02Z)
• Beyond Semantic IDs: Encoding Business-Value Ranking into Document Identifiers for Generative Retrieval [28.485766948414206]
  Generative Retrieval (GR) formulates retrieval as a sequence-to-sequence generation task, assigning each document a document identifier (DocID) and retrieving it through autoregressive decoding.<n>Existing schemes based on discrete representation learning suffer from inherent collision issues.<n>We propose Cluster-Ranked Identifier (CRID), which decouples DocID into semantic clustering and business-value ranking, yielding collision-free identifiers.
  arXiv  Detail & Related papers  (2026-07-13T10:57:20Z)
• Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization [68.48718919047127]
  Multimodal generative retrieval formulates multimodal retrieval as discrete identifier generation, eliminating the need for explicit similarity search over external embeddings.<n>Existing approaches construct identifiers via residual quantization and decode them with trie-constrained beam search.<n>This combination introduces an indexing-decoding gap: identifier learning objectives, including reconstruction and contrastive losses, do not explicitly enforce prefix discriminability during decoding.<n>We propose PRO, a unified framework comprising three mechanisms: (i) prefix ranking distillation aligns quantized prefixes with those induced by pre-quantization embeddings using a listwise loss; (ii) vocabulary scheduling increases codebook
  arXiv  Detail & Related papers  (2026-06-08T09:15:47Z)
• Aligning Large Language Models with Searcher Preferences [26.974618053554394]
  We introduce SearchLLM, the first large language model (LLM) for open-ended generative search.<n>We design a hierarchical, multi-dimensional reward system that separates bottom-line constraints.<n> offline evaluations and online A/B tests show improved generation quality and user engagement.
  arXiv  Detail & Related papers  (2026-03-11T06:44:30Z)
• MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains [79.14584837105808]
  We present MC-Search, the first benchmark for agentic MM-RAG with long, step-wise annotated reasoning chains spanning five representative reasoning structures.<n>Beyond answer accuracy, MC-Search introduces new process-level metrics for reasoning quality, stepwise retrieval and planning accuracy.<n>By developing a unified agentic MM-RAG pipeline, we benchmark six leading MLLMs and reveal systematic issues such as over- and under-retrieval and modality-misaligned planning.
  arXiv  Detail & Related papers  (2026-03-01T02:25:57Z)
• Learning to Route: A Rule-Driven Agent Framework for Hybrid-Source Retrieval-Augmented Generation [55.47971671635531]
  Large Language Models (LLMs) have shown remarkable performance on general Question Answering (QA)<n>Retrieval-Augmented Generation (RAG) addresses this limitation by enriching LLMs with external knowledge.<n>Existing systems primarily rely on unstructured documents, while largely overlooking relational databases.
  arXiv  Detail & Related papers  (2025-09-30T22:19:44Z)
• OneSearch: A Preliminary Exploration of the Unified End-to-End Generative Framework for E-commerce Search [43.94443394870866]
  OneSearch is the first industrial-deployed end-to-end generative framework for e-commerce search.<n>OneSearch reduces operational expenditure by 75.40% and improves Model FLOPs Utilization from 3.26% to 27.32%.<n>The system has been successfully deployed across multiple search scenarios in Kuaishou, serving millions of users.
  arXiv  Detail & Related papers  (2025-09-03T11:50:04Z)
• Constrained Auto-Regressive Decoding Constrains Generative Retrieval [71.71161220261655]
  Generative retrieval seeks to replace traditional search index data structures with a single large-scale neural network.<n>In this paper, we examine the inherent limitations of constrained auto-regressive generation from two essential perspectives: constraints and beam search.
  arXiv  Detail & Related papers  (2025-04-14T06:54:49Z)
• Faster Learned Sparse Retrieval with Block-Max Pruning [11.080810272211906]
  This paper introduces Block-Max Pruning (BMP), an innovative dynamic pruning strategy tailored for indexes arising in learned sparse retrieval environments. BMP substantially outperforms existing dynamic pruning strategies, offering unparalleled efficiency in safe retrieval contexts.
  arXiv  Detail & Related papers  (2024-05-02T09:26:30Z)
• How Does Generative Retrieval Scale to Millions of Passages? [68.98628807288972]
  We conduct the first empirical study of generative retrieval techniques across various corpus scales. We scale generative retrieval to millions of passages with a corpus of 8.8M passages and evaluating model sizes up to 11B parameters. While generative retrieval is competitive with state-of-the-art dual encoders on small corpora, scaling to millions of passages remains an important and unsolved challenge.
  arXiv  Detail & Related papers  (2023-05-19T17:33:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.