Problem
Research questions and friction points this paper is trying to address.
Define rationality in artificial intelligence agents.
Explore optimal irrational behaviors in AI scenarios.
Analyze human-AI interaction and rationality roles.
(Ir)rationality in AI: State of the Art, Research Challenges and Open Questions
🤖 AI Summary
This paper addresses the fundamental challenge in AI research: the lack of a unified definition of “rationality.” It systematically examines the conceptual evolution of rationality and irrationality and their behavioral manifestations in human–AI interaction and adversarial settings. Through interdisciplinary theoretical analysis—drawing on philosophy, economics, and cognitive psychology—complemented by behavioral modeling and human–AI collaborative rationality assessment, the study establishes the first unified analytical framework for AI irrationality research and introduces the novel concept of “beneficial irrationality.” It identifies seven functionally optimal yet formally irrational behavioral patterns, articulates four core challenges confronting AI rationality research, and demonstrates the critical role of irrationality in enhancing robustness, explainability, and ethical adaptability. The findings provide foundational theoretical support for explainable AI, robust human–AI collaboration, and ethically grounded AI design.
📝 Abstract
The concept of rationality is central to the field of artificial intelligence. Whether we are seeking to simulate human reasoning, or the goal is to achieve bounded optimality, we generally seek to make artificial agents as rational as possible. Despite the centrality of the concept within AI, there is no unified definition of what constitutes a rational agent. This article provides a survey of rationality and irrationality in artificial intelligence, and sets out the open questions in this area. The understanding of rationality in other fields has influenced its conception within artificial intelligence, in particular work in economics, philosophy and psychology. Focusing on the behaviour of artificial agents, we consider irrational behaviours that can prove to be optimal in certain scenarios. Some methods have been developed to deal with irrational agents, both in terms of identification and interaction, however work in this area remains limited. Methods that have up to now been developed for other purposes, namely adversarial scenarios, may be adapted to suit interactions with artificial agents. We further discuss the interplay between human and artificial agents, and the role that rationality plays within this interaction; many questions remain in this area, relating to potentially irrational behaviour of both humans and artificial agents.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Survey of rationality in AI
Adapted methods for irrational agents
Interplay between human and AI agents
🔎 Similar Papers
No similar papers found.
