The Self-and-Self-and-World Model: A General Computational Framework for Adaptive Coordination Between Internal Computational Mechanisms and World-State Modeling
Abstract
Computational systems increasingly operate in environments where successful behavior depends on both the organization of internal computation and the ability to represent, predict, and respond to external conditions. A system may possess multiple internal computational mechanisms for generation, diagnosis, verification, correction, planning, and evaluation, while also maintaining a model of the world in which its decisions are executed. However, internal mechanism selection and world-state modeling are often treated as separate design problems. This separation can limit a system's ability to determine not only what it should compute, but also which aspects of its world model require additional computation, when internal mechanisms should be activated, and when predicted consequences justify further investigation.
This paper proposes the Self-and-Self-and-World Model (SSWM), a general computational framework for adaptively coordinating internal computational mechanisms with world-state modeling. The framework distinguishes three interacting dimensions: the system's internal computational state, the organization of its internal mechanisms, and its representation of the external world. Its central principle is that a computational system should jointly determine how to allocate internal computation and how to maintain or revise its world model according to task requirements, uncertainty, prediction error, expected utility, environmental change, and computational constraints.
SSWM formalizes the internal mechanism repertoire, world-state representation, model uncertainty, mechanism-dependent model updates, action-conditioned predictions, computational costs, and feedback-driven adaptation. It introduces a coupled decision formulation in which mechanism selection and world-model maintenance can influence one another. The paper presents a reference architecture, a proposed algorithm, conditional theoretical propositions, complexity considerations, experimental hypotheses, and a cross-domain evaluation program.
SSWM is intended as an organizational abstraction for systems that must coordinate internal computation with representations of external conditions, including autonomous agents, robotics, planning, scientific computing, and model-based decision systems. Its distinct contribution, if supported by formal analysis and empirical evidence, would be a unified account of how internal mechanism organization and world-model management can be jointly adapted rather than optimized independently. The framework is proposed for investigation; its novelty, advantages, and generality require systematic comparison with existing research on world models, metareasoning, model-based planning, adaptive computation, and active information acquisition.
Related
- The Self-and-Self Model: A General Computational Framework for Adaptive Selection and Coordination Among Internal Computational Mechanisms
- The Self-and-World Model: A General Computational Framework for Adaptive Coordination Between Internal Computation and World-State Modeling
- The Self-and-Mutual-and-World Model: A General Computational Framework for Adaptive Coordination Between Autonomous Computation, Interactive Mechanisms, and World-State Modeling
- The Self-and-Mutual-and-Meta Model: A General Computational Framework for Adaptive Coordination, Selection, and Regulation of Autonomous and Interactive Mechanisms
- The Self-and-Mutual-and-Causality Model: A General Computational Framework for Adaptive Coordination Between Individual Processing, Interactive Mechanisms, and Causal Reasoning
BibTeX
@misc{zhang2026selfandselfandworld,
title = {{The Self-and-Self-and-World Model: A General Computational Framework for Adaptive Coordination Between Internal Computational Mechanisms and World-State Modeling}},
author = {Jincheng Zhang},
howpublished = {Zenodo},
year = {2026},
month = oct,
doi = {10.5281/zenodo.23432955},
url = {https://zenodo.org/records/23432955},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - The Self-and-Self-and-World Model: A General Computational Framework for Adaptive Coordination Between Internal Computational Mechanisms and World-State Modeling
AU - Jincheng Zhang
PY - 2026
DA - 2026/10/17
PB - Zenodo
DO - 10.5281/zenodo.23432955
UR - https://zenodo.org/records/23432955
AB - Computational systems increasingly operate in environments where successful behavior depends on both the organization of internal computation and the ability to represent, predict, and respond to external conditions. A system may possess multiple internal computational mechanisms for generation, diagnosis, verification, correction, planning, and evaluation, while also maintaining a model of the world in which its decisions are executed. However, internal mechanism selection and world-state modeling are often treated as separate design problems. This separation can limit a system's ability to determine not only what it should compute, but also which aspects of its world model require additional computation, when internal mechanisms should be activated, and when predicted consequences justify further investigation. This paper proposes the Self-and-Self-and-World Model (SSWM), a general computational framework for adaptively coordinating internal computational mechanisms with world-state modeling. The framework distinguishes three interacting dimensions: the system's internal computational state, the organization of its internal mechanisms, and its representation of the external world. Its central principle is that a computational system should jointly determine how to allocate internal computation and how to maintain or revise its world model according to task requirements, uncertainty, prediction error, expected utility, environmental change, and computational constraints. SSWM formalizes the internal mechanism repertoire, world-state representation, model uncertainty, mechanism-dependent model updates, action-conditioned predictions, computational costs, and feedback-driven adaptation. It introduces a coupled decision formulation in which mechanism selection and world-model maintenance can influence one another. The paper presents a reference architecture, a proposed algorithm, conditional theoretical propositions, complexity considerations, experimental hypotheses, and a cross-domain evaluation program. SSWM is intended as an organizational abstraction for systems that must coordinate internal computation with representations of external conditions, including autonomous agents, robotics, planning, scientific computing, and model-based decision systems. Its distinct contribution, if supported by formal analysis and empirical evidence, would be a unified account of how internal mechanism organization and world-model management can be jointly adapted rather than optimized independently. The framework is proposed for investigation; its novelty, advantages, and generality require systematic comparison with existing research on world models, metareasoning, model-based planning, adaptive computation, and active information acquisition.
ER -