用大模型协调检索，提升数据集搜索的准确性和可审计性。
A Reference Architecture for Agentic Hybrid Retrieval in Dataset Search
- 大模型驱动混合检索，结合关键词与向量匹配，动态优化查询。
- 引入伪查询增强元数据，缓解用户意图与元数据间的语义差异。
- 提供可扩展的参考架构，适合关注系统可审计性的研发团队。
即兴数据集搜索需将模糊的自然语言查询与稀疏、异构的元数据记录匹配，传统词法或稠密检索难以胜任。本文将数据集搜索重构为软件架构问题，提出一种边界可控、可审计的代理型混合检索参考架构：通过大语言模型（LLM）代理协调BM25词法检索与稠密嵌入检索，利用倒数排名融合（RRF）整合结果，并实现多轮查询规划、结果评估与候选重排。为缓解用户意图与提供商撰写元数据之间的词汇不匹配问题，引入离线元数据增强步骤——由LLM为每条数据集记录生成伪查询，扩充检索索引。考察两种架构风格：单一ReAct代理与具有反馈控制的多代理横向架构，从可修改性、可观测性、性能和治理性维度分析其权衡。定义包含七个系统变体的评估框架，以隔离各架构决策的贡献。该架构作为可扩展的参考设计，为软件架构社区提供显式治理策略，用于约束和审计非确定性LLM组件。
原文摘要 · Abstract (English)
Ad hoc dataset search requires matching underspecified natural-language queries against sparse, heterogeneous metadata records, a task where typical lexical or dense retrieval alone falls short. We reposition dataset search as a software-architecture problem and propose a bounded, auditable reference architecture for agentic hybrid retrieval that combines BM25 lexical search with dense-embedding retrieval via reciprocal rank fusion (RRF), orchestrated by a large language model (LLM) agent that repeatedly plans queries, evaluates the sufficiency of results, and reranks candidates. To reduce the vocabulary mismatch between user intent and provider-authored metadata, we introduce an offline metadata augmentation step in which an LLM generates pseudo-queries for each dataset record, augmenting both retrieval indexes before query time. Two architectural styles are examined: a single ReAct agent and a multi-agent horizontal architecture with Feedback Control. Their quality-attribute tradeoffs are analyzed with respect to modifiability, observability, performance, and governance. An evaluation framework comprising seven system variants is defined to isolate the contribution of each architectural decision. The architecture is presented as an extensible reference design for the software architecture community, incorporating explicit governance tactics to bound and audit nondeterministic LLM components.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。