The Universal Self-Mutual-Human Planning Framework: Adaptive Selection, Switching, Combination, and Reconfiguration of Planning Mechanisms Among Artificial Intelligence Models and Human Participants

Planning is a fundamental capability of intelligent systems, enabling participants to establish objectives, decompose tasks, organize actions, allocate resources, anticipate constraints, and determine strategies for achieving desired outcomes. Existing research has investigated autonomous planning, multi-agent collaborative planning, human–AI planning, distributed planning, and mixed-initiative planning. However, these approaches are frequently investigated through separate operational configurations, specific planning architectures, or predefined interaction arrangements. A general theoretical framework that integrates individual self-directed planning, collaborative planning among multiple participants, and human planning while dynamically selecting and switching among these mechanisms remains an important research direction. This paper introduces the Universal Self-Mutual-Human Adaptive Planning Framework (USMHM-APF), a mechanism-independent extension of the Universal Self-Mutual-Human Model (USMHM). The proposed framework establishes three fundamental planning dimensions: Self-Planning, in which an individual artificial intelligence model, autonomous agent, human, or other participant independently develops and manages a plan; Collaborative Planning, in which multiple participants jointly formulate, evaluate, negotiate, integrate, and coordinate plans; and Human Planning, in which human individuals or groups independently formulate plans or actively participate in guiding, modifying, approving, and coordinating planning processes. The central contribution is the integration of these three dimensions within a unified adaptive planning architecture. Rather than permanently assigning a planning task to one mechanism, the framework enables an intelligent system to adaptively determine whether a task should be handled through Self-Planning, Collaborative Planning, Human Planning, or combinations of these mechanisms. It further supports dynamic switching between planning configurations during task formulation, decomposition, evaluation, execution, monitoring, and replanning. The framework distinguishes adaptive planning adjustment, mechanism selection, mechanism switching, collaborative combination, and structural reconfiguration. A formal representation, adaptive decision model, planning transition architecture, operational lifecycle, theoretical propositions, governance principles, and evaluation methodology are developed. To the best of our knowledge, this paper is the first to formally unify Self-Planning, Collaborative Planning, and Human Planning within the USMHM conceptual architecture while explicitly integrating mechanism-independent adaptive selection, dynamic switching, combination, and reconfiguration across heterogeneous human and artificial participants. The proposed framework provides a general theoretical foundation for designing and analyzing planning systems that can dynamically determine not only what should be planned, but also who should participate in planning, how planning should be conducted, and when the planning mechanism should change.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-18
DOI
https://doi.org/10.5281/zenodo.24338874
Primary Topic
AI-based Problem Solving and Planning
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

The Universal Self-Mutual-Human Planning Framework: Adaptive Selection, Switching, Combination, and Reconfiguration of Planning Mechanisms Among Artificial Intelligence Models and Human Participants

Jincheng Zhang
3 links
Zenodo (CERN European Organization for Nuclear Research)
AI-based Problem Solving and Planning
preprint

The Universal Self-Mutual-Human Planning Framework: Adaptive Selection, Switching, Combination, and Reconfiguration of Planning Mechanisms Among Artificial Intelligence Models and Human Participants

Jincheng Zhang
preprint en

Abstract

Planning is a fundamental capability of intelligent systems, enabling participants to establish objectives, decompose tasks, organize actions, allocate resources, anticipate constraints, and determine strategies for achieving desired outcomes. Existing research has investigated autonomous planning, multi-agent collaborative planning, human–AI planning, distributed planning, and mixed-initiative planning. However, these approaches are frequently investigated through separate operational configurations, specific planning architectures, or predefined interaction arrangements. A general theoretical framework that integrates individual self-directed planning, collaborative planning among multiple participants, and human planning while dynamically selecting and switching among these mechanisms remains an important research direction. This paper introduces the Universal Self-Mutual-Human Adaptive Planning Framework (USMHM-APF), a mechanism-independent extension of the Universal Self-Mutual-Human Model (USMHM). The proposed framework establishes three fundamental planning dimensions: Self-Planning, in which an individual artificial intelligence model, autonomous agent, human, or other participant independently develops and manages a plan; Collaborative Planning, in which multiple participants jointly formulate, evaluate, negotiate, integrate, and coordinate plans; and Human Planning, in which human individuals or groups independently formulate plans or actively participate in guiding, modifying, approving, and coordinating planning processes. The central contribution is the integration of these three dimensions within a unified adaptive planning architecture. Rather than permanently assigning a planning task to one mechanism, the framework enables an intelligent system to adaptively determine whether a task should be handled through Self-Planning, Collaborative Planning, Human Planning, or combinations of these mechanisms. It further supports dynamic switching between planning configurations during task formulation, decomposition, evaluation, execution, monitoring, and replanning. The framework distinguishes adaptive planning adjustment, mechanism selection, mechanism switching, collaborative combination, and structural reconfiguration. A formal representation, adaptive decision model, planning transition architecture, operational lifecycle, theoretical propositions, governance principles, and evaluation methodology are developed. To the best of our knowledge, this paper is the first to formally unify Self-Planning, Collaborative Planning, and Human Planning within the USMHM conceptual architecture while explicitly integrating mechanism-independent adaptive selection, dynamic switching, combination, and reconfiguration across heterogeneous human and artificial participants. The proposed framework provides a general theoretical foundation for designing and analyzing planning systems that can dynamically determine not only what should be planned, but also who should participate in planning, how planning should be conducted, and when the planning mechanism should change.

Zenodo (CERN European Organization for Nuclear Research)
AI-based Problem Solving and Planning
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