Abstract--Deep-sea exploration faces critical challenges including disorientation, communication loss, and navigational failures in hostile underwater environments. This paper presents an Autonomous Underwater Cognitive System (AUCS) that integrates Simultaneous Localization and Mapping (SLAM) with a Soar-based cognitive architecture to enable adaptive navigation under dynamic oceanic conditions. The system combines multi-sensor fusion (SONAR, LiDAR, IMU, DVL) with cognitive reasoning capabilities including perception, attention, planning, and learning. Unlike conventional reactive SLAM systems, AUCS incorporates semantic understanding, adaptive sensor management, and memory-based learning to distinguish between dynamic and static objects, thus reducing false loop closures and improving long-term map consistency. This work addresses critical safety limitations observed in previous deep-sea missions and establishes a foundation for next-generation cognitive submersible systems.

Abstract--A new AUV mission planning and execution software has been tested on AUV Sentry. Dubbed DINOS-R, it draws inspiration from cognitive architectures and AUV control systems to replace the legacy MC architecture. Unlike these existing architectures, however, DINOS-R is built from the ground-up to unify symbolic decision making (for understandable, repeatable, provable behavior) with machine learning techniques and reactive behaviors, for field-readiness across oceanographic platforms. Implemented primarily in Python3, DINOS-R is extensible, modular, and reusable, with an emphasis on non-expert use as well as growth for future research in oceanography and robot algorithms. Mission specification is flexible, and can be specified declaratively. Behavior specification is similarly flexible, supporting simultaneous use of real-time task planning and hard-coded user specified plans. These features were demonstrated in the field on Sentry, in addition to a variety of simulated cases. These results are discussed, and future work is outlined. In particular, although the MC (Mission Controller) system in use on AUV Sentry has repeatedly proven itself for lawnmower patterns, it presents several key limitations stemming from its rigid implementation. Most notably, it is capable of executing basic "go-to" commands and similar functionality, but was not engineered for scalability to new mission modalities or real-time interventions.

The study of emergent behaviors in large language model (LLM)-driven multi-agent systems is a critical research challenge, yet progress is limited by a lack of principled methodologies for controlled experimentation. To address this, we introduce Shachi, a formal methodology and modular framework that decomposes an agent's policy into core cognitive components: Configuration for intrinsic traits, Memory for contextual persistence, and Tools for expanded capabilities, all orchestrated by an LLM reasoning engine. This principled architecture moves beyond brittle, ad-hoc agent designs and enables the systematic analysis of how specific architectural choices influence collective behavior. We validate our methodology on a comprehensive 10-task benchmark and demonstrate its power through novel scientific inquiries. Critically, we establish the external validity of our approach by modeling a real-world U.S. tariff shock, showing that agent behaviors align with observed market reactions only when their cognitive architecture is appropriately configured with memory and tools. Our work provides a rigorous, open-source foundation for building and evaluating LLM agents, aimed at fostering more cumulative and scientifically grounded research.

Evaluation is a critical activity associated with any theory. Yet this has proven to be a n exceptionally challenging activity for theories based on cognitive architectures. For an overlapping set of reasons, evaluation can also be challenging for theories based on generative neural architectures. T h is dual challenge is approached here by leveraging a broad perspective on theory evaluation to yield a wide - ranging, albeit qualitative, comparison of whole - mind - orie n ted cognitive and generative architectures an d the full systems th a t are based on these architectures .

Human-machine interaction is increasingly important in industry, and this trend will only intensify with the rise of Industry 5.0. Human operators have skills that need to be adapted when using machines to achieve the best results. It is crucial to highlight the operator's skills and understand how they use and adapt them [18]. A rigorous description of these skills is necessary to compare performance with and without robot assistance. Predicate logic, used by Vergnaud within Piaget's scheme concept, offers a promising approach. However, this theory doesn't account for cognitive system constraints, such as the timing of actions, the limitation of cognitive resources, the parallelization of tasks, or the activation of automatic gestures contrary to optimal knowledge. Integrating these constraints is essential for representing agent skills understanding skill transfer between biological and mechanical structures. Cognitive architectures models [2] address these needs by describing cognitive structure and can be combined with the scheme for mutual benefit. Welding provides a relevant case study, as it highlights the challenges faced by operators, even highly skilled ones. Welding's complexity stems from the need for constant skill adaptation to variable parameters like part position and process. This adaptation is crucial, as weld quality, a key factor, is only assessed afterward via destructive testing. Thus, the welder is confronted with a complex perception-decision-action cycle, where the evaluation of the impact of his actions is delayed and where errors are definitive. This dynamic underscores the importance of understanding and modeling the skills of operators.

Our framework, HARMONIC (Human-AI Robotic Team Member Operating with Natural Intelligence and Communication, Figure 1), is an implemented dual-control cognitive robotic architecture featuring distinct layers of strategic reasoning and tactical, skill-level control [20]. This approach advances the hybrid control systems and architectures reviewed by Dennis et al. [21] and contrasts with DIARC's [22], [23] integration strategy, which embeds the strategic layer within the tactical layer to support concurrent operation. The strategic layer of HARMONIC adapts a mature cognitive architecture, OntoAgent [24], [25], [17] for high-level reasoning, leveraging explicit, structured knowledge representations that can be inspected, verified, and incre-mentally expanded.

Computational cognitive architectures are broadly scoped models of the human mind that combine different psychological functionalities (as well as often different computational methods for these different functionalities) into one unified framework. They structure them in a psychologically plausible and validated way. However, such models thus far have only limited computational capabilities, mostly limited by the computational tools and techniques that were adopted. More recently, LLMs have proved to be more capable computationally than any other tools. Thus, in order to deal with both real-world complexity and psychological realism at the same time, incorporating LLMs into cognitive architectures naturally becomes an important task. In the present article, a synergistic combination of the Clarion cognitive architecture and LLMs is discussed as a case study. The implicit-explicit dichotomy that is fundamental to Clarion is leveraged for a seamless integration of Clarion and LLMs. As a result, computational power of LLMs is combined with psychological nicety of Clarion.

The article provides an overview of approaches to modeling the human psyche in the perspective of building an artificial one. Based on the review, a concept of cognitive architecture is proposed, where the psyche is considered as an operating system of a living or artificial subject, including a space of needs that determines its life meanings in connection with stimuli from the external world, and intelligence as a decision-making system for actions in relation to this world in order to satisfy these needs. Based on the concept, a computational formalization is proposed for creating artificial intelligence systems through learning from experience in the space of a space of needs, taking into account their biological or existential significance for an intelligent agent. Thus, the problem of building general artificial intelligence as a system for making optimal decisions in the space of agent-specific needs under conditions of uncertainty is formalized, with maximization of success in achieving goals, minimization of existential risks and maximization of energy efficiency. A minimal experimental implementation of the model is also provided.

What is it about human brains that allows us to reason symbolically whereas most other animals cannot? There is evidence that dynamic binding, the ability to combine neurons into groups on the fly, is necessary for symbolic thought, but there is also evidence that it is not sufficient. We propose that two kinds of hierarchical integration (integration of multiple role-bindings into multiplace predicates, and integration of multiple correspondences into structure mappings) are minimal requirements, on top of basic dynamic binding, to realize symbolic thought. We tested this hypothesis in a systematic collection of 17 simulations that explored the ability of cognitive architectures with and without the capacity for multi-place predicates and structure mapping to perform various kinds of tasks. The simulations were as generic as possible, in that no task could be performed based on any diagnostic features, depending instead on the capacity for multi-place predicates and structure mapping. The results are consistent with the hypothesis that, along with dynamic binding, multi-place predicates and structure mapping are minimal requirements for basic symbolic thought. These results inform our understanding of how human brains give rise to symbolic thought and speak to the differences between biological intelligence, which tends to generalize broadly from very few training examples, and modern approaches to machine learning, which typically require millions or billions of training examples. The results we report also have important implications for bio-inspired artificial intelligence.

Holographic Declarative Memory (HDM) is a vector-symbolic alternative to ACT-R's Declarative Memory (DM) system that can bring advantages such as scalability and architecturally defined similarity between DM chunks. We adapted HDM to work with the most comprehensive and widely-used implementation of ACT-R (Lisp ACT-R) so extant ACT-R models designed with DM can be run with HDM without major changes. With this adaptation of HDM, we have developed vector-based versions of common ACT-R functions, set up a text processing pipeline to add the contents of large documents to ACT-R memory, and most significantly created a useful and novel mechanism to retrieve an entire chunk of memory based on a request using only vector representations of tokens. Preliminary results indicate that we can maintain vector-symbolic advantages of HDM (e.g., chunk recall without storing the actual chunk and other advantages with scaling) while also extending it so that previous ACT-R models may work with the system with little (or potentially no) modifications within the actual procedural and declarative memory portions of a model. As a part of iterative improvement of this newly translated holographic declarative memory module, we will continue to explore better time-context representations for vectors to improve the module's ability to reconstruct chunks during recall. To more fully test this translated HDM module, we also plan to develop decision-making models that use instance-based learning (IBL) theory, which is a useful application of HDM given the advantages of the system.