Get started
Work

NMCA (Neurosymbolic Multimodal Cognitive Architecture) Addendum - 2026

Year: 2026
Type: preprint
Abstract: This architectural addendum accompanies the 2026 NMCA (Neurosymbolic Multimodal Cognitive Architecture) blueprint and provides a consolidated cognitive map and tools and implementation assessment for all 128 proposed modules. The purpose of this addendum is to clarify what the 128-module architecture is intended to represent as a possible artificial mind, how the proposed functions relate to one another, and which aspects can currently be attempted with available software and engineering tools. The architecture was not designed as a minimum viable AI system or solely as a task-oriented tool. Its underlying design goal is to explore what would be required for an artificial mind capable of persistent identity, memory, visual-symbolic thought, emotional regulation, social cognition. The cognitive map therefore distinguishes between primary cognitive functions, functions that may be implemented as part of other modules, and surrounding infrastructure such as multi-agent environments, development tooling, testing systems, and containment mechanisms. All 128 original module headings are retained; this addendum does not replace, revise, or supersede the original NMCA blueprint. The accompanying tools map provides a separate 2026 assessment of what can currently be attempted with available software. It distinguishes between capabilities for which useful implementation machinery exists, capabilities for which only significant partial components exist, and functions for which no established software stack currently provides a convincing implementation. The existence of a tool or library is not treated as evidence that the corresponding cognitive function has been solved. This document is an architectural and conceptual assessment, not a claim that NMCA has been implemented, or that every proposed module is independently necessary. It is intended to make the architecture's functional assumptions, design goal, and present-day implementation landscape explicit for future researchers, engineers, and reviewers. This addendum is provided as a companion reference explaining the cognitive interpretation and current technological feasibility of the proposed architecture. Status: Theoretical specification with minimum viable loop descriptions. A complete running system is not claimed. Intended for research, sandbox simulation, and human-guided exploration. Not for autonomous deployment. I chose to release all versions freely to the public. I did this because the implications of proprietary, corporate-controlled systems built on visual thought / internal 3D simulation as a core of cognition are too large to leave exclusively in private hands. The work is therefore placed in the public record so that the chronological priority and the original architectural claims remain visible. The final specification is the 471-page NMCA blueprint published in 2026. Earlier versions remain preserved as separate historical records. Publication Chronology Date Publication Record April 20, 2025 Original 46-page NMCA blueprint Zenodo DOI 10.5281/zenodo.21972901 2026 Expanded NMCA architecture Zenodo DOI 10.5281/zenodo.20212241 2026 NMCA Architectural Addendum Zenodo DOI 10.5281/zenodo.22352561 What was disclosed on April 20, 2025 Internal 3D Scene Builder used to simulate tasks visually and model interactions Persistent internal visual/3D scene representation for reasoning Memory encoding that stores visual scenes for future recall Internal visual simulation synchronized with observation Symbolic scene representations tied to memory and belief structures Contradiction detection and belief updating Planning inside the 3D spatial model Simulation of routes and actions before execution Feedback from real observation that triggers replanning Multiple simulation branches Explicit computational loop: Input → Internal Simulation → Action → Reflective Update Concrete example given in the original disclosure: An agent is told to get a banana from the refrigerator. It loads the refrigerator location from prior visual memory, internally simulates the full route and object interaction, executes the plan, discovers the refrigerator is empty, and generates a new subgoal. Final blueprint version: https://zenodo.org/records/20212241 Project site: https://visualthoughtagi.com Mirror: https://visualthoughtagi.netlify.app Demo: (illustration of the distinction, not the full architecture): https://derekv123.itch.io/visual-thought-agi --- Final 471-page blueprint DOI: https://doi.org/10.5281/zenodo.20212241 Final 471-page blueprint IPFS CID: bafybeiedxfq5wsvuayjcxcxwmtto6ptelznkj6arb4mrscshwhcc2selfm Final 471-page blueprint IPFS Download ----- Original 46-page blueprint DOI: https://doi.org/10.5281/zenodo.21972901 --- Original 46-page blueprint IPFS CID: bafybeifjiyzm6tmk2jj27tjvbpqgdqpjm5loeon6y6ikxzeek3ff2vbdey --- Original 46-page blueprint IPFS Download USPTO prior-art copy filed. No patent pursued --- Addendum to the 471-page blueprint DOI: https://doi.org/10.5281/zenodo.22352561 --- Addendum to the 471-page blueprint IPFS CID: bafkreibse76prz3wypp3tcveczq4iuoifmk6sp5e73cbqiz2sry6b3hmvy --- Addendum to the 471-page blueprint IPFS Download --- ORCID: https://orcid.org/0009-0008-4149-5384 Alternative Research Download Sites OSFAcademia Attribution of the 2026 NMCA All derivatives must prominently cite: “Neurosymbolic Multimodal Cognitive Architecture (NMCA) - by Derek Van Derven (2026).” This requirement applies to derivatives of the 2026 work. Earlier publications may have different licensing terms; the license attached to the specific version should be consulted. License: CC BY-NC-SA 4.0 Cite both DOIs, with the 2025 publication first. 22352561 (addendum) Companion to 20212241; cite 20212241 and 21972901
DOI: 10.5281/zenodo.22352560
Language: English
Open Access status: green
OpenAlex ID: W7208821122
Cites:
Cited by:
Related to: