Adaptive Self–Human Search: A Universal Framework for Autonomous Search, Human-Directed Information Seeking, and Dynamic Switching Between Artificial Intelligence and Human Search

The rapid development of large language models (LLMs) and autonomous AI agents has substantially expanded the ways in which information can be discovered, retrieved, explored, evaluated, and synthesized. Contemporary intelligent systems can independently formulate search queries, access external information sources, conduct iterative retrieval, refine search strategies, and assess retrieved evidence. Nevertheless, human search remains essential for activities requiring contextual understanding, specialized knowledge, independent investigation, unconventional information discovery, and critical judgment. Although existing research has extensively investigated information retrieval, interactive information seeking, exploratory search, conversational search, human–AI collaboration, and autonomous search agents, these areas commonly emphasize particular search technologies, interaction patterns, or task-specific architectures. A general mechanism-independent framework that treats AI self-search and human search as distinct but combinable functional dimensions, and dynamically determines which should conduct a search, when responsibility should transfer, and when both should search together, remains insufficiently formalized. This paper introduces Adaptive Self–Human Search (ASHS), a universal conceptual framework that extends the Universal Self–Human Model (USHM) into the functional domain of information seeking and search execution. ASHS establishes two fundamental dimensions: Self-Search (S), representing search activities performed autonomously by an AI system through its own computational and agentic mechanisms, and Human Search (H), representing search activities independently performed or substantively directed by human individuals or groups. These dimensions produce three non-empty operational configurations: Self-Search, Human Search, and Self–Human Search. Unlike architectures that permanently assign search responsibility to either an AI system or a human participant, ASHS treats search configuration as an adaptive operational decision. It introduces Universal Search Functional Generality, Adaptive Search Mechanism Selection, Adaptive Search Mechanism Switching, Adaptive Search Combination, and Adaptive Search Reconfiguration. The framework further formalizes search-state representation, information sufficiency, uncertainty, evidence quality, search costs, transition conditions, and responsibility allocation. It also establishes principles for source diversity, independent verification, human authority, information provenance, and search accountability. To the best of our knowledge, this paper is the first to formally articulate a mechanism-independent, function-general architecture specifically unifying autonomous AI self-search and independently performed human search through adaptive configuration selection, switching, combination, and reconfiguration as its central organizing principle. This priority claim concerns the particular theoretical integration and architecture proposed here, rather than the broader fields of information retrieval, human information seeking, conversational search, or agentic search. The paper establishes a conceptual foundation for intelligent systems that can dynamically determine whether information should be searched for by AI, by humans, or through an adaptive combination of both.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-19
DOI
https://doi.org/10.5281/zenodo.24359908
Primary Topic
Information Retrieval and Search Behavior
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Adaptive Self–Human Search: A Universal Framework for Autonomous Search, Human-Directed Information Seeking, and Dynamic Switching Between Artificial Intelligence and Human Search

Jincheng Zhang
Zenodo (CERN European Organization for Nuclear Research)
Information Retrieval and Search Behavior
preprint

Adaptive Self–Human Search: A Universal Framework for Autonomous Search, Human-Directed Information Seeking, and Dynamic Switching Between Artificial Intelligence and Human Search

Jincheng Zhang
preprint en

Abstract

The rapid development of large language models (LLMs) and autonomous AI agents has substantially expanded the ways in which information can be discovered, retrieved, explored, evaluated, and synthesized. Contemporary intelligent systems can independently formulate search queries, access external information sources, conduct iterative retrieval, refine search strategies, and assess retrieved evidence. Nevertheless, human search remains essential for activities requiring contextual understanding, specialized knowledge, independent investigation, unconventional information discovery, and critical judgment. Although existing research has extensively investigated information retrieval, interactive information seeking, exploratory search, conversational search, human–AI collaboration, and autonomous search agents, these areas commonly emphasize particular search technologies, interaction patterns, or task-specific architectures. A general mechanism-independent framework that treats AI self-search and human search as distinct but combinable functional dimensions, and dynamically determines which should conduct a search, when responsibility should transfer, and when both should search together, remains insufficiently formalized. This paper introduces Adaptive Self–Human Search (ASHS), a universal conceptual framework that extends the Universal Self–Human Model (USHM) into the functional domain of information seeking and search execution. ASHS establishes two fundamental dimensions: Self-Search (S), representing search activities performed autonomously by an AI system through its own computational and agentic mechanisms, and Human Search (H), representing search activities independently performed or substantively directed by human individuals or groups. These dimensions produce three non-empty operational configurations: Self-Search, Human Search, and Self–Human Search. Unlike architectures that permanently assign search responsibility to either an AI system or a human participant, ASHS treats search configuration as an adaptive operational decision. It introduces Universal Search Functional Generality, Adaptive Search Mechanism Selection, Adaptive Search Mechanism Switching, Adaptive Search Combination, and Adaptive Search Reconfiguration. The framework further formalizes search-state representation, information sufficiency, uncertainty, evidence quality, search costs, transition conditions, and responsibility allocation. It also establishes principles for source diversity, independent verification, human authority, information provenance, and search accountability. To the best of our knowledge, this paper is the first to formally articulate a mechanism-independent, function-general architecture specifically unifying autonomous AI self-search and independently performed human search through adaptive configuration selection, switching, combination, and reconfiguration as its central organizing principle. This priority claim concerns the particular theoretical integration and architecture proposed here, rather than the broader fields of information retrieval, human information seeking, conversational search, or agentic search. The paper establishes a conceptual foundation for intelligent systems that can dynamically determine whether information should be searched for by AI, by humans, or through an adaptive combination of both.

Zenodo (CERN European Organization for Nuclear Research)
Information Retrieval and Search Behavior
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon