arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.17518cs.IR
收藏

代理搜索的图景

A Picture of Agentic Search

University of Pisa(比萨大学);Georgetown University(乔治城大学);Sapienza University of Rome(罗马第一大学);University of Glasgow(格拉斯哥大学)

Francesca Pezzuti, Ophir Frieder, Fabrizio Silvestri, Sean MacAvaney, Nicola Tonellotto

AI总结:

本文提出了一种收集代理检索增强系统生成和消耗数据的方法,并发布了一个包含多代理和检索流程的数据集,以应对IR在代理用户需求下的适应性挑战。

摘要:

随着自动化系统越来越多地与人类一同发出搜索查询,信息检索(IR)正面临重大转变。然而,IR仍然以人类为中心,系统、评估指标、用户模型和数据集都是围绕人类查询和行为设计的。因此,IR在实践中所基于的假设已不再成立,工作量的变化、可预测性和查询行为都发生了变化。这种不一致影响了系统性能和优化:缓存可能失效,查询预处理可能增加开销而不改善结果,标准指标可能错误衡量满意度。没有适应,检索模型可能既不满足人类,也不满足新兴的代理用户群体。然而,捕捉代理搜索行为的数据集却缺乏,这给IR的历史依赖数据驱动评估和优化带来了关键缺口。我们开发了一种方法,用于收集所有由代理检索增强系统回答查询时生成和消耗的数据,并发布了代理搜索查询集(ASQ)数据集。ASQ包含在HotpotQA、Researchy Questions和MS MARCO中生成的推理诱导查询、检索文档和查询的思考,涵盖3种不同的代理和2种检索流程。配套的工具包使ASQ能够扩展到新的代理、检索器和数据集。

英文摘要:

With automated systems increasingly issuing search queries alongside humans, Information Retrieval (IR) faces a major shift. Yet IR remains human-centred, with systems, evaluation metrics, user models, and datasets designed around human queries and behaviours. Consequently, IR operates under assumptions that no longer hold in practice, with changes to workload volumes, predictability, and querying behaviours. This misalignment affects system performance and optimisation: caching may lose effectiveness, query pre-processing may add overhead without improving results, and standard metrics may mismeasure satisfaction. Without adaptation, retrieval models risk satisfying neither humans, nor the emerging user segment of agents. However, datasets capturing agent search behaviour are lacking, which is a critical gap given IR's historical reliance on data-driven evaluation and optimisation. We develop a methodology for collecting all the data produced and consumed by agentic retrieval-augmented systems when answering queries, and we release the Agentic Search Queryset (ASQ) dataset. ASQ contains reasoning-induced queries, retrieved documents, and thoughts for queries in HotpotQA, Researchy Questions, and MS MARCO, for 3 diverse agents and 2 retrieval pipelines. The accompanying toolkit enables ASQ to be extended to new agents, retrievers, and datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑