A Modular Cognitive Architecture for Assisted Reasoning: The Nemosine Framework

TL;DR

The paper identifies a need for an integrated cognitive framework to support structured reasoning and reduce cognitive load, addressing gaps in existing tools. It presents Nemosine, a modular, function-driven architecture built from coordinated cognitive agents designed to enable guided problem solving, perspective shifting, and metacognitive reflection, with a design-science development process. An exploratory evaluation with 21 participants suggests the framework is clear, coherent, and perceived as beneficial for organizing complex thoughts, though it does not provide empirical performance validation. The work lays a foundation for future computational implementations and hybrid human–AI systems that support structured reasoning in real-world tasks.

Abstract

This paper presents the Nemosine Framework, a modular cognitive architecture designed to support assisted reasoning, structured thinking, and systematic analysis. The model operates through functional cognitive modules ("personas") that organize tasks such as planning, evaluation, cross-checking, and narrative synthesis. The framework combines principles from metacognition, distributed cognition, and modular cognitive systems to offer an operational structure for assisted problem-solving and decision support. The architecture is documented through formal specification, internal consistency criteria, and reproducible structural components. The goal is to provide a clear conceptual basis for future computational implementations and to contribute to the study of symbolic-modular architectures for reasoning.