MetaMo Robust Motivational Framework

help edit space_dashboard
Draft — This content has not been approved for publication.
ai generated
open_in_full page
fullscreen modal
edit edit
space_dashboard advanced
motivation
open_in_full page
fullscreen modal
edit create
space_dashboard advanced
publication:paper
open_in_full page
fullscreen modal
edit create
space_dashboard advanced
Authors: Ben Goertzel, Ruiting Lian

← Back to Publications

MetaMo: A Robust Motivational Framework for Open-Ended AGI

Authors:

Ben Goertzel
Ruiting Lian

Year: 2025
Venue: AGI 2025
Links: no public URL yet; see the public source context below

Summary

The abstract theory paper for MetaMo. It presents a unified motivational framework combining category theory, functional analysis, and topology to describe open-ended agents that can self-modify without collapsing motivational coherence. The paper centers on a composite appraisal-then-decision operator with comonadic and monadic structure, plus contractive updates and tubular topology guarantees that keep motivational change inside a feasible region.

Relevance to Hyperon

This is the formal foundation behind MetaMo Deep Dive and one of the key theory papers for the motivation layer in the current Hyperon stack. It is also directly relevant to Magi Full, because MAGUS and related systems are framed as concrete motivational realizations rather than unrelated products.

Key References



Discussion

Implementation & component card: a Python reference implementation exists at iCog-Labs-Dev/MetaMo-Python (verified by the Cross-Org sweeps, HAA S2); the predecessor OpenPsi substrate is iCog-Labs-Dev/hyperon-openpsi. See the MetaMo Deep Dive.