NAEL: Non-Anthropocentric Ethical Logic

2025-10-16

AI Summary

This paper addresses the overreliance on anthropocentric assumptions in AI ethics by proposing a non-anthropocentric, dynamic ethical framework. Methodologically, it integrates active inference with symbolic logic to construct a neurosymbolic architecture, enabling agents to autonomously balance self-preservation, epistemic exploration, and collective welfare in multi-agent environments—through minimization of global free energy—thereby yielding context-sensitive, relational, and adaptive ethical behavior. Its key contribution is reconceptualizing ethicality as an emergent system-level property of dynamic equilibrium under uncertainty, decoupling it from human moral intuition. Experiments demonstrate that the framework autonomously evolves context-aware ethical decision-making in resource-allocation tasks, offering a computationally grounded and empirically verifiable paradigm for non-anthropocentric AI ethics.

Technology Category

• Philosophy and Ethics of AI: Artificial General Intelligence
• Humans and AI: Learning Human Values and Preferences
• Multiagent Systems: Agent/AI Theories and Architectures

Application Category

• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We introduce NAEL (Non-Anthropocentric Ethical Logic), a novel ethical framework for artificial agents grounded in active inference and symbolic reasoning. Departing from conventional, human-centred approaches to AI ethics, NAEL formalizes ethical behaviour as an emergent property of intelligent systems minimizing global expected free energy in dynamic, multi-agent environments. We propose a neuro-symbolic architecture to allow agents to evaluate the ethical consequences of their actions in uncertain settings. The proposed system addresses the limitations of existing ethical models by allowing agents to develop context-sensitive, adaptive, and relational ethical behaviour without presupposing anthropomorphic moral intuitions. A case study involving ethical resource distribution illustrates NAEL's dynamic balancing of self-preservation, epistemic learning, and collective welfare.

Problem

• Developing ethical AI framework beyond human-centered approaches
• Formalizing emergent ethical behavior in multi-agent environments
• Addressing limitations of existing models with adaptive ethical reasoning

Innovation

• Novel ethical framework using active inference
• Neuro-symbolic architecture for ethical evaluation
• Dynamic balancing of self-preservation and welfare