Zobrazit v EDS

ARCHITECTING SUPERINTELLIGENT AGENTS: A HIERARCHICAL META-LEARNING FRAMEWORK FOR CONTINUAL REASONING, MEMORY EVOLUTION, AND GOAL SELF-GENERATION FOR EMERGENT GENERAL INTELLIGENCE

Uloženo v:
Podrobná bibliografie
Název: ARCHITECTING SUPERINTELLIGENT AGENTS: A HIERARCHICAL META-LEARNING FRAMEWORK FOR CONTINUAL REASONING, MEMORY EVOLUTION, AND GOAL SELF-GENERATION FOR EMERGENT GENERAL INTELLIGENCE
Autoři: Researcher
Informace o vydavateli: Zenodo, 2025.
Rok vydání: 2025
Témata: AGI, Meta-Learning, Continual Reasoning, World Modeling, Introspective Planning, Goal Self-Generation, Dynamic Value Alignment, Memory Evolution, Cognitive Architectures, Self-Supervised Learning
Popis: In the pursuit of Artificial General Intelligence (AGI), architecting superintelligent agents remains an enduring challenge. This paper introduces a hierarchical meta-learning framework designed for continual reasoning, dynamic memory evolution, and autonomous goal generation. We present a synthesis of world modeling, introspective planning, and real-time value alignment as a foundation for emergent intelligence. Drawing from biologically inspired cognition, this architecture aims to replicate core features of flexible learning and self-improving inference. Our proposal integrates a scalable memory structure, adaptive reward modeling, and modular self-reflection, addressing key constraints in long-term agent autonomy and open-ended learning.
Druh dokumentu: Article
Jazyk: English
DOI: 10.5281/zenodo.15679737
DOI: 10.5281/zenodo.15679736
Rights: CC BY
Přístupové číslo: edsair.doi.dedup.....092f2d14d5ecf00315b2eae264e8b02c
Databáze: OpenAIRE
Popis
Abstrakt:In the pursuit of Artificial General Intelligence (AGI), architecting superintelligent agents remains an enduring challenge. This paper introduces a hierarchical meta-learning framework designed for continual reasoning, dynamic memory evolution, and autonomous goal generation. We present a synthesis of world modeling, introspective planning, and real-time value alignment as a foundation for emergent intelligence. Drawing from biologically inspired cognition, this architecture aims to replicate core features of flexible learning and self-improving inference. Our proposal integrates a scalable memory structure, adaptive reward modeling, and modular self-reflection, addressing key constraints in long-term agent autonomy and open-ended learning.
DOI:10.5281/zenodo.15679737