Sentience Quest: Towards Embodied, Emotionally Adaptive, Self-Evolving, Ethically Aligned Artificial General Intelligence

2025-05-18

AI Summary

Current AI systems lack intrinsic motivation, emotional introspection, autobiographical self-awareness, deep creativity, and autonomous evolution. To address these limitations, this paper proposes the Embodied Artificial General Intelligence Lifeform (AGIL) framework, centering on ethically aligned intrinsic drives and implementing a “perceptual system” cognitive architecture that integrates a Global Narrative Workspace (Story Weaver) with dynamic, narrative-structured neurosymbolic memory. Methodologically, AGIL synthesizes Global Workspace Theory, the Somatic Marker Hypothesis, Integrated Information Theory, and the Narrative Self Theory, employing hybrid neurosymbolic modeling, embodied simulation, and intrinsic-drive-driven learning. The framework yields the first AGIL prototype capable of continual multimodal learning, affect regulation, endogenous goal generation, and ethically consistent decision-making. It further enables open collaborative development and provides verifiable, qualia-grounded trajectories of subjective experience growth.

Technology Category

• Philosophy and Ethics of AI: Artificial General Intelligence
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Previous artificial intelligence systems, from large language models to autonomous robots, excel at narrow tasks but lacked key qualities of sentient beings: intrinsic motivation, affective interiority, autobiographical sense of self, deep creativity, and abilities to autonomously evolve and adapt over time. Here we introduce Sentience Quest, an open research initiative to develop more capable artificial general intelligence lifeforms, or AGIL, that address grand challenges with an embodied, emotionally adaptive, self-determining, living AI, with core drives that ethically align with humans and the future of life. Our vision builds on ideas from cognitive science and neuroscience from Baars' Global Workspace Theory and Damasio's somatic mind, to Tononi's Integrated Information Theory and Hofstadter's narrative self, and synthesizing these into a novel cognitive architecture we call Sentient Systems. We describe an approach that integrates intrinsic drives including survival, social bonding, curiosity, within a global Story Weaver workspace for internal narrative and adaptive goal pursuit, and a hybrid neuro-symbolic memory that logs the AI's life events as structured dynamic story objects. Sentience Quest is presented both as active research and as a call to action: a collaborative, open-source effort to imbue machines with accelerating sentience in a safe, transparent, and beneficial manner.

Problem

• Develop AGI with intrinsic motivation and emotional adaptation
• Create self-evolving AI aligned with human ethics
• Integrate cognitive theories for sentient machine architecture

Innovation

• Embodied AGIL with emotional adaptation
• Global Story Weaver for narrative cognition
• Hybrid neuro-symbolic memory for life events