Article

Toward a reusable architecture for intelligent agents

2025-07-28

Abstract excerpt

<p>Active inference provides a powerful framework for understanding how agents perceive, learn, and act by maintaining an internal model of the world. However, most existing implementations rely on generative models that are designed for specific tasks or domains. These task specific models limit the ability of agents to generalise, adapt to new environments, or scale beyond narrow applications.Taking inspiration...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 89d155e2-7582-55ab-90f9-6c587dd8d24a
DOI: 10.31234/osf.io/6nxf3_v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Toward a reusable architecture for intelligent agentsDOI 10.31234/osf.io/6nxf3_v1Read

Recursive self-models and minimal phenomenal experienceSemantic proximity Read

Constrained Object Hierarchies as a Unified Theoretical Model for Intelligence and Intelligent SystemsSemantic proximity Read

CogNGen: Constructing the kernel of a hyperdimensional predictive processing cognitive architectureSemantic proximity Read

From Pre-Trained Language Models to Agentic AI: Evolution and Architectures for Autonomous IntelligenceSemantic proximity Read

Episodic Question Answering for Cognitive AgentsSemantic proximity Read

Toward the Emergence of Intelligent Control: Episodic Generalization and OptimizationSemantic proximity Read

Preparing humanity for change and artificial intelligenceSemantic proximity Read

Rethink Your Mental Model in the Age of Generative AI: A Triadic Framework for Human-AI CollaborationSemantic proximity Read

Learning generalizable representations through efficient codingSemantic proximity Read

Learning generalizable representations through efficient codingSemantic proximity Read

Learning generalizable representations through efficient codingSemantic proximity Read

Integrated World Modeling Theory (IWMT) Expanded: Implications for Theories of Consciousness and Artificial IntelligenceSemantic proximity Read