A Design Science Framework for Human-Agent Teams in Information Retrieval

Abstract

Multi-agent information retrieval is not a future prospect -- it is an operational reality. Existing frameworks for multi-agent coordination -- including comprehensive taxonomies of collaboration mechanisms and adaptive orchestration architectures for modular generative IR systems -- address the agent-only case: they configure AI components that interact with each other to serve a passive human end-user. The heterogeneous case -- teams in which humans and AI agents serve as joint cognitive participants with complementary capabilities -- remains without a principled design foundation. This perspectives paper introduces the Collaborative Information Retrieval Configurations (CIRC) framework, organized around three dimensions -- composition, coordination, and adaptation -- that provide systematic guidance for designing and evaluating human-agent teams in IR. Situated within the design science research paradigm, CIRC is prescriptive where prior taxonomies are descriptive: it specifies when collaborative configurations outperform single-agent approaches, which coordination patterns suit which task types, and how to evaluate team-level performance rather than individual agent output. We ground the framework in simulation experiments on TREC Deep Learning 2020 that demonstrate the framework's discriminative capacity: collaborative configurations produce measurably distinct quality profiles, and collaborative advantages concentrate at higher task complexity in ways that standard IR metrics fail to capture. We outline a three-dimensional evaluation framework and a concrete research agenda to advance the science of collaborative IR configurations.