close fullscreen

Hyperon Wiki Extensions+MetaMo (legacy duplicate)

help edit space_dashboard

MetaMo (Motivational Framework)

Responsible: Ruiting Lian, Ben Goertzel

GitHub: https://github.com/iCog-Labs-Dev/hyperon-openpsi

Papers:

  • Lian, R., Goertzel, B. MetaMo: A Robust Motivational Framework for Open-Ended AGI. (AGI 2025)
  • Lian, R., Goertzel, B. Embodying Abstract Motivational Principles in Concrete AGI Systems: From MetaMo to Open-Ended OpenPsi. (AGI 2025)

Description:

MetaMo is a framework for modeling motivation in open-ended intelligent agents, concerned with how goals, priorities, and evaluative signals can be updated over time while preserving coherence, stability, and interpretability. Rather than relying on scalar reward functions or manually engineered drive hierarchies, MetaMo treats motivation itself as a dynamical system, explicitly coupling appraisal processes with decision processes.

MetaMo represents motivational state as a structured interaction between goal intensities and modulatory variables. Appraisal updates modulators such as valence, arousal, and risk sensitivity in response to contextual novelty and task relevance, while decision mechanisms score candidate actions relative to active goals. System stability is enforced via contractive update dynamics that draw motivational state away from pathological extremes.

Within the Hyperon ecosystem, MetaMo serves as the motivational backbone linking inference, learning, and attention allocation. It shapes control dynamics in PLN by biasing search and inference toward contextually appropriate goals, regulates exploration–exploitation tradeoffs, and embeds safety and ethical constraints directly within motivational dynamics rather than as externally imposed rules.

Roadmap:

  • Formalize pseudo-bimonad structure and five design principles; prove stability via contractive updates
  • Implement OpenPsi (appraisal comonad) and MAGUS (decision monad) with dual overgoals
  • Embed MetaMo into Hyperon Atomspace and PLN for motivation-guided inference
  • Build a research assistant demo, validate inference allocation, and test multi-agent coordination
  • Refine blending dynamics, develop verification methods, and benchmark against other AI approaches