NAEL: Non-Anthropocentric Ethical Logic

TL;DR

NAEL proposes a non-anthropocentric framework for AI ethics by formulating ethical action as the minimization of a global expected free energy $\,\mathcal{G}_{global}\,$ in dynamic multi-agent environments. It fuses active inference with neuro-symbolic reasoning, leveraging deontic, standpoint, and subjective logics to reason about norms, perspectives, and epistemic uncertainty. The global objective $\,\mathcal{G}_{global} = \sum_{i=1}^N \mathbb{E}_{Q_i}[\mathcal{F}_i] + \mathcal{F}_{env}$ guides policy across agents, promoting relational, adaptive ethics that respect ecological and inter-agent interdependence. A resource-allocation case study in an arid valley demonstrates how perception, deliberation, and action selection are integrated to balance self-preservation, knowledge gathering, and collective welfare. This approach aims to enable ethically coherent behavior in environments where human-centric norms are insufficient or inappropriate, with potential applications in conservation, climate-sensitive planning, and multi-agent governance, while acknowledging current computational and verification challenges.

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.