Efficiently Linking Unstructured Data for Multi-step Reasoning

原文：Efficiently Linking Unstructured Data for Multi-step Reasoning

作者：Jiaming Liang, Haydn Jones, Jacob R. Gardner, Mark Yatskar, Zachary Ives

来源：arXiv cs.DB（数据库）

正文

Computer Science > Databases

arXiv:2609.19491v1 (cs)

[Submitted on 16 Sep 2026]

Title:Efficiently Linking Unstructured Data for Multi-step Reasoning

Authors:Jiaming Liang, Haydn Jones, Jacob R. Gardner, Mark Yatskar, Zachary Ives

View a PDF of the paper titled Efficiently Linking Unstructured Data for Multi-step Reasoning, by Jiaming Liang and 4 other authors

View PDF

HTML (experimental)

Abstract:Modern LLMs and AI agents increasingly support data engineering workflows that integrate evidence from unstructured sources. Such pipelines typically do data retrieval, integration, and ranking before proceeding to more complex agentic reasoning or actions, e.g., for scientific discovery. The core retrieval problem in these workflows jointly executes multi-attribute filtering, multi-vector search, exact relational joins, and thresholded embedding-similarity joins. Given a planned query and monotone scoring function, our DASE query engine constructs and ranks candidate evidence tuples. It comprises (i) a multi-step reasoning query model over structured predicates, multiple vectors, and relational links; (ii) SemJI, a sparse materialized embedding-similarity join index for rare near-neighbor pairs; and (iii) a co-designed execution layer that combines predicate-aware ANN traversal, batched access, and threshold-based score aggregation.

On scientific-discovery workloads, DASE retrieves candidate evidence for multi-step reasoning queries 6x to 46x faster than strong RDBMS, rerank, and vector-database baselines at comparable recall; and for tasks that require semantic-operator post-processing, DASE acts as a high-recall prefilter that makes downstream LLM evaluation both cheaper and more accurate – e.g., on SemBench E-Commerce it improves BigQuery quality from 0.67 to 0.80 while cutting cost from $2.42 to $0.54.

Comments:

23 pages, 9 figures

Subjects:

Databases (cs.DB); Artificial Intelligence (cs.AI)

Cite as:

arXiv:2609.19491 [cs.DB]

(or

arXiv:2609.19491v1 [cs.DB] for this version)

https://doi.org/10.48550/arXiv.2609.19491

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

数据库 · 人工智能

由「前沿雷达」于 2026-09-17 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。