This paper introduces the System 0/1/2/3 framework as an extension of dual-process theory, employing a quad-process model of cognition. Expanding upon System 1 (fast, intuitive thinking) and System 2 (slow, deliberative thinking), we incorporate System 0, which represents pre-cognitive embodied processes, and System 3, which encompasses collective intelligence and symbol emergence. We contextualize this model within Bergson's philosophy by adopting multi-scale time theory to unify the diverse temporal dynamics of cognition. System 0 emphasizes morphological computation and passive dynamics, illustrating how physical embodiment enables adaptive behavior without explicit neural processing. Systems 1 and 2 are explained from a constructive perspective, incorporating neurodynamical and AI viewpoints. In System 3, we introduce collective predictive coding to explain how societal-level adaptation and symbol emergence operate over extended timescales. This comprehensive framework ranges from rapid embodied reactions to slow-evolving collective intelligence, offering a unified perspective on cognition across multiple timescales, levels of abstraction, and forms of human intelligence. The System 0/1/2/3 model provides a novel theoretical foundation for understanding the interplay between adaptive and cognitive processes, thereby opening new avenues for research in cognitive science, AI, robotics, and collective intelligence.

The ability to adapt and switch between tasks is a fundamental Empirical studies further established the prefrontal cortex aspect of cognitive flexibility, shaping decision-making (PFC) as a key region in task-switching, with experiments such and behavioral efficiency in dynamic environments. Taskswitching as the Wisconsin Card Sorting Test (WCST) demonstrating its has been widely studied across disciplines such as role in adaptive behavior [14]-[16]. Spiking Neural Networks psychology, cognitive neuroscience, and artificial intelligence (SNNs) have emerged as a biologically realistic approach to [1], [2]. While humans often shift between tasks seamlessly, modeling neural dynamics, particularly due to their ability to performance variations arise depending on prior experience, replicate synaptic plasticity mechanisms such as Spike Timing-task familiarity, and cognitive load. Understanding these processes Dependent Plasticity (STDP) [10], [17]. Prior studies have requires computational models that can capture the successfully applied SNNs to pattern recognition and classification underlying neural mechanisms driving adaptive control and tasks [18] and have modeled sensory processing systems decision-making. Empirical studies have identified increased like the mammalian olfactory system [19]. These findings neural activity in the cognitive control network, particularly in establish a computational foundation for implementing taskswitching the prefrontal cortex (PFC), when engaging in task-switching models with biologically grounded learning dynamics.

Artificial intelligence (AI) systems, from large language models (LLMs) to reinforcement learning agents, now exhibit behaviours once assumed to be exclusive to humans and other animals. As such, researchers are increasingly probing these systems using psychological methods, asking questions about how they explore new environments, make decisions in risky conditions, and reason about their own uncertainty [1]. This work appears to be driven by two motivations: better characterising what AI can and cannot do so that we can improve it and use it safely; and the tantalising proposition that AI constitutes a new class of cognitive system worthy of serious scientific attention, not only to learn more about how they work but to better understand our own cognition [2]. But applying methods designed for human cognitive psychology to test AI risks both under-and over-attributing cognitive capacities to them - because those tests may be ill-designed for these non-human subjects. Comparative cognition - the study of non-human animal behaviour - has grappled with similar challenges for decades. By adopting its methods, AI research could avoid pitfalls, join the cognitive sciences, and clarify the nature of cognition itself.

Inspired by human cognition, metacognition has gained significant attention for its potential to enhance autonomy, adaptability, and robust learning in artificial agents. Yet research on Computational Metacognitive Architectures (CMAs) remains fragmented: diverse theories, terminologies, and design choices have led to disjointed developments and limited comparability across systems. Existing overviews and surveys often remain at a broad, conceptual level, making it difficult to synthesize deeper insights into the underlying algorithms and representations, and their respective success. We address this gap by performing an explorative systematic review of how CMAs model, store, remember and process their metacognitive experiences, one of Flavell's (1979) three foundational components of metacognition. Following this organizing principle, we identify 35 CMAs that feature episodic introspective data ranging from symbolic event traces to sub-symbolic arousal metrics. We consider different aspects - ranging from the underlying psychological theories to the content and structure of collected data, to the algorithms used and evaluation results - and derive a unifying perspective that allows us to compare in depth how different Computational Metacognitive Architectures (CMAs) leverage metacognitive experiences for tasks such as error diagnosis, self-repair, and goal-driven learning. Our findings highlight both the promise of metacognitive experiences - in boosting adaptability, explainability, and overall system performance - and the persistent lack of shared standards or evaluation benchmarks.

Artificial Intelligence increasingly pursues large, complex models that perform many tasks within increasingly realistic domains. How, if at all, should these developments in AI influence cognitive science? We argue that progress in AI offers timely opportunities for cognitive science to embrace experiments with increasingly naturalistic stimuli, tasks, and behaviors; and computational models that can accommodate these changes. We first review a growing body of research spanning neuroscience, cognitive science, and AI that suggests that incorporating a broader range of naturalistic experimental paradigms (and models that accommodate them) may be necessary to resolve some aspects of natural intelligence and ensure that our theories generalize. We then suggest that integrating recent progress in AI and cognitive science will enable us to engage with more naturalistic phenomena without giving up experimental control or the pursuit of theoretically grounded understanding. We offer practical guidance on how methodological practices can contribute to cumulative progress in naturalistic computational cognitive science, and illustrate a path towards building computational models that solve the real problems of natural cognition - together with a reductive understanding of the processes and principles by which they do so.

Metacognition is the concept of reasoning about an agent's own internal processes, and it has recently received renewed attention with respect to artificial intelligence (AI) and, more specifically, machine learning systems. This paper reviews a hybrid-AI approach known as "error detecting and correcting rules" (EDCR) that allows for the learning of rules to correct perceptual (e.g., neural) models. Additionally, we introduce a probabilistic framework that adds rigor to prior empirical studies, and we use this framework to prove results on necessary and sufficient conditions for metacognitive improvement, as well as limits to the approach. A set of future

Vision-language-action (VLA) models hold promise as generalist robotics solutions by translating visual and linguistic inputs into robot actions, yet they lack reliability due to their black-box nature and sensitivity to environmental changes. In contrast, cognitive architectures (CA) excel in symbolic reasoning and state monitoring but are constrained by rigid predefined execution. This work bridges these approaches by probing OpenVLA's hidden layers to uncover symbolic representations of object properties, relations, and action states, enabling integration with a CA for enhanced interpretability and robustness. Through experiments on LIBERO-spatial pick-and-place tasks, we analyze the encoding of symbolic states across different layers of OpenVLA's Llama backbone. Our probing results show consistently high accuracies (> 0.90) for both object and action states across most layers, though contrary to our hypotheses, we did not observe the expected pattern of object states being encoded earlier than action states. We demonstrate an integrated DIARC-OpenVLA system that leverages these symbolic representations for real-time state monitoring, laying the foundation for more interpretable and reliable robotic manipulation.

In this work, we propose Perspective Reasoning for Integrated Synthesis and Mediation (PRISM), a multiple-perspective framework for addressing persistent challenges in AI alignment such as conflicting human values and specification gaming. Grounded in cognitive science and moral psychology, PRISM organizes moral concerns into seven "basis worldviews", each hypothesized to capture a distinct dimension of human moral cognition, ranging from survival-focused reflexes through higher-order integrative perspectives. It then applies a Pareto-inspired optimization scheme to reconcile competing priorities without reducing them to a single metric. Under the assumption of reliable context validation for robust use, the framework follows a structured workflow that elicits viewpoint-specific responses, synthesizes them into a balanced outcome, and mediates remaining conflicts in a transparent and iterative manner. By referencing layered approaches to moral cognition from cognitive science, moral psychology, and neuroscience, PRISM clarifies how different moral drives interact and systematically documents and mediates ethical tradeoffs. We illustrate its efficacy through real outputs produced by a working prototype, applying PRISM to classic alignment problems in domains such as public health policy, workplace automation, and education. By anchoring AI deliberation in these human vantage points, PRISM aims to bound interpretive leaps that might otherwise drift into non-human or machine-centric territory. We briefly outline future directions, including real-world deployments and formal verifications, while maintaining the core focus on multi-perspective synthesis and conflict mediation.

Approximately at the same time, based on the ideas This work proposes an approach that uses an evolutionary presented by Newell, Rosenbloom and Laird (1989), Laird algorithm along traditional Machine Learning methods released early versions of the SOAR cognitive architecture to build a digital, distributed cognitive agent capable of (Laird and Rosenbloom, 1996; Laird, 2012). By the end of emulating the potential actions (input-output behavior) of the 1990s, a large group of researchers involved in the Simulation a user while allowing further analysis and experimentation of Adaptive Behavior shaped the concept of Cognitive - at a certain level - of its internal structures. We focus Architecture as an essential set of structures and processes on the usage of simple devices and the automation of this necessary for the generation of a computational, cognitive building process, rather than manually designing the agent.

Many studies have evaluated the cognitive alignment of Pre-trained Language Models (PLMs), i.e., their correspondence to adult performance across a range of cognitive domains. Recently, the focus has expanded to the developmental alignment of these models: identifying phases during training where improvements in model performance track improvements in children's thinking over development. However, there are many challenges to the use of PLMs as cognitive science theories, including different architectures, different training data modalities and scales, and limited model interpretability. In this paper, we distill lessons learned from treating PLMs, not as engineering artifacts but as cognitive science and developmental science models. We review assumptions used by researchers to map measures of PLM performance to measures of human performance. We identify potential pitfalls of this approach to understanding human thinking, and we end by enumerating criteria for using PLMs as credible accounts of cognition and cognitive development.