Bounded Morality: Defining the Space of Moral Computation
arXiv:2607.00002 [cs.AI]
Submitted on 1 Apr 2026
Authors: Max Kanwal, Caryn Tran, Patrick Mineault
Abstract
Moral cognition has traditionally been modeled as adherence to fixed ethical theories—deontology, consequentialism, and virtue ethics—implemented as static rules or value functions. In this paper, we propose Bounded Morality, a formal framework for analyzing the computational demands of moral problems faced by finite agents. Extending Herbert Simon's concept of bounded rationality, we characterize moral situations along two orthogonal dimensions: moral breadth—the scope of entities treated as morally relevant—and moral depth—the inferential integration required to evaluate their interactions. Limited computational resources impose an unavoidable tradeoff between these dimensions, defining a feasible space of moral computation.
Within this space, ethical theories correspond to locally efficient strategies adapted to different demand regimes, rather than competing accounts of moral truth. The framework yields formal notions of moral regret and moral progress under constraint, and suggests that moral alignment in artificial systems depends on the scaling and allocation of moral reasoning capacity—not on direct imitation of human judgments.
Comments
24 pages, 2 figures. Presented at the AAAI-26 Workshop on Machine Ethics.
Subjects
- Artificial Intelligence (cs.AI)
- Computers and Society (cs.CY)
Cite as
Kanwal, M., Tran, C., & Mineault, P. (2026). Bounded Morality: Defining the Space of Moral Computation. arXiv:2607.00002 [cs.AI]. https://doi.org/10.48550/arXiv.2607.00002
Submission History
Version 1 – Submitted by Max Kanwal on Wednesday, 1 April 2026, 17:35:43 UTC (85 KB).
via ArXiv AI