Oscar J. Romero

• Researcher
• Researcher at Carnegie Mellon University

This paper explores the integration of two AI subdisciplines employed in the development of artificial agents that exhibit intelligent behavior: Large Language Models (LLMs) and Cognitive Architectures (CAs). We present three integration approaches, each grounded in theoretical models and supported by preliminary empirical evidence. The modular app...

This article explores the integration of two AI subdisciplines employed in the development of artificial agents that exhibit intelligent behavior: Large Language Models (LLMs) and Cognitive Architectures (CAs). We present three integration approaches, each grounded in theoretical models and supported by preliminary empirical evidence. The modular a...

This paper presents exploratory work on how the key components of transformer-based neural language models (self-attention mechanism and large-scale pre-trained models) can be leveraged to perform context retrieval, symbol manipulation, and propositional reasoning. We fine-tuned GPT-X language models to learn Prolog programs that simulate the propo...

Recently, transformer language models have been applied to build both task-and non-task-oriented dialogue systems. Although transformers perform well on most of the NLP tasks, they perform poorly on context retrieval and symbolic reasoning. Our work aims to address this limitation by embedding the model in an operational loop that blends both natur...

Personalization of user experience has a long history of success in the HCI community. More recently the community has focused on adaptive user interfaces, supported by machine learning, that reduce interaction efforts and improves user experience by collapsing transactions and pre-filtering results. However, generally, these more recent results ha...

Natural language interfaces have become a common part of modern digital life. Chatbots utilize text-based conversations to communicate with users; personal assistants on smartphones such as Google Assistant take direct speech commands from their users; and speech-controlled devices such as Amazon Echo use voice as their only input mode. In this pap...

Natural language interfaces have become a common part of modern digital life. Chatbots utilizetext-based conversations to communicate with users; personal assistants on smartphones such asGoogle Assistant take direct speech commands from their users; and speech-controlled devices suchas Amazon Echo use voice as their only input mode. In this paper,...

Natural language interfaces have become a common part of modern digital life. Chatbots utilize text-based conversations to communicate with users; personal assistants on smartphones such as Google Assistant take direct speech commands from their users; and speech-controlled devices such as Amazon Echo use voice as their only input mode. In this pap...

Automatic service composition in mobile and pervasive computing faces many challenges due to the complex and highly dynamic nature of the environment. Common approaches consider service composition as a decision problem whose solution is usually addressed from optimization perspectives which are not feasible in practice due to the in-tractability o...

Automatic service composition in mobile and pervasive computing faces many challenges due to the complex nature of the environment. Common approaches address service composition from optimization perspectives which are not feasible in practice due to the intractability of the problem, limited computational resources of smart devices, service host's...

Automatic service composition in mobile and pervasive computing faces many challenges due to the complex and highly dynamic nature of the environment. Common approaches consider service composition as a decision problem whose solution is usually addressed from optimization perspectives which are not feasible in practice due to the intractability of...

Intelligent Personal Assistants (IPAs) are software agents that can perform tasks on behalf of individuals and assist them on many of their daily activities. IPAs capabilities are expanding rapidly due to the recent advances on areas such as natural language processing, machine learning, artificial cognition, and ubiquitous computing, which equip t...

As smartphones become increasingly more powerful, a new generation of highly interactive user-centric mobile apps emerge to make user's life simpler and more productive. Mobile phones applications have to sustain limited resource availability on mobile devices such as battery life, network connectivity while also providing better responsiveness, li...

As smartphones become increasingly more powerful, a new generation of highly interactive user-centric mobile apps emerge to make user's life simpler and more productive. Mobile phones applications have to sustain limited resource availability on mobile devices such as battery life, network connectivity while also providing better responsiveness, li...

Automatic service composition in mobile and pervasive computing faces many challenges due to the complex nature of the environment. Common approaches address service composition from optimization perspectives which are not feasible in practice due to the intractability of the problem, limited computational resources of smart devices, service host's...

Automatic service composition in mobile and pervasive computing faces many challenges due to the complex and highly dynamic nature of the environment. Common approaches consider service composition as a decision problem whose solution is usually addressed from optimization perspectives which are not feasible in practice due to the intractability of...

As smartphones become increasingly more powerful, a new generation of highly interactive user-centric mobile apps emerge to make user's life simpler and more productive. However, the construction of such apps requires developers to spend a considerable amount of time dealing with the architecture constraints imposed by the wide variety of platforms...

Current approaches for service composition (as-semblies of atomic services) require developers to use: (a) domain-specific semantics to formalize services that restrict the vocabulary for their descriptions, and (b) translation mechanisms for service retrieval to convert unstructured user requests to strongly-typed semantic representations. In our...

Network Science has reported a considerable amount of human-subject experiments on which individuals have to carry out different kind of coordination games such as coloring and consensus problems in order to observe the behavioral dynamics behind the decision-making process. We have focused on the experiments carried out by Kearns (Kearns, 2010) on...

Current approaches for service composition (assemblies of atomic services) require developers to use: (a) domain-specific semantics to formalize services that restrict the vocabulary for their descriptions, and (b) translation mechanisms for service retrieval to convert unstructured user requests to strongly-typed semantic representations. In our w...

This paper provides a starting point for the development of metacognition in a common model of cognition. It identifies significant theoretical work on metacognition from multiple disciplines that the authors believe worthy of consideration. After first defining cognition and metacognition, we outline three general categories of metacognition, prov...

In this paper, we propose a semi-automatic social intelligent negotiation dialogue system that interweaves task utterance with conversational strategies to engage human users in negotiation. Our two-phase system operates sequentially in a reasoning-and-generation loop: In the task phase, we leverage an off-the-shelf end-to-end dialogue model for ne...

We present the input to the discussion about the computational framework known as Common Model of Cognition (CMC) from the working group dealing with the knowledge/rational/social levels. In particular, we present a list of the higher level constraints that should be addressed within such a general framework.

As the Common Model of Cognition (CMC) is getting more supporters from research fields such as AI, cognitive science, neuroscience, and robotics in an effort to contribute to the understanding of minds, a new requirement becomes imperative: standard modeling and specification mechanisms are needed to allow both developing new CMC-compliant computat...

This paper provides a starting point for the development of metacognition in a common model of cognition. It identifies significant theoretical work on metacognition from multiple disciplines that the authors believe worthy of consideration. After first defining cognition and metacognition, we outline three general categories of metacognition, prov...

The growing use of mobile and wearables devices has opened a broad range of possibilities for building robust Intelligent Personal Assistants (IPA's). Most known IPA's implementations have predominantly focused on understanding what the user's immediate intention is, however, there is no evidence of trying to understand the user's context and inten...

In this work we propose a novel module for a dialogue system that allows a conversational agent to utter phrases that do not just meet the system's task intentions, but also work towards achieving the system's social intentions. The module - a Social Reasoner - takes the task goals the system must achieve and decides the appropriate conversational...

With recent advances in robotics technologies and autonomous systems, the idea of human-robot teams is gaining ever-increasing attention. In this context, our research focuses on developing an intelligent robot that can autonomously perform non-trivial, but specific tasks conveyed through natural language. Toward this goal, a consortium of research...

Robots are increasingly becoming key players in human-robot teams. To become effective teammates, robots must possess profound understanding of an environment, be able to reason about the desired commands and goals within a specific context, and be able to communicate with human teammates in a clear and natural way. To address these challenges, we...

Robots are increasingly becoming key players in human-robot teams. To become effective teammates, robots must possess profound understanding of an environment , be able to reason about the desired commands and goals within a specific context, and be able to communicate with human teammates in a clear and natural way. To address these challenges, we...

We propose ideas for a test of for human-like intelligence inspired by constraints recent advancements from from cognitive science on theories of cognition. The most salient characteristics of the this test include the capacity for open-ended, generative behavior, the ability to learn and adapt in real time in complex environments, and the ability...

The Network Science has dedicated a considerable amount of effort to the study of many distributed collective decision-making processes which must balance diverse individual preferences with an expectation for collective unity. Several works have reported their results about behavioral experiments on biased voting in networks individuals, however w...

En el campo de estudio de los Agentes Autónomos Inteligentes, uno de los retos más complejos de lograr es la simulación de los procesos cognitivos. En la presente tesis, se propone un modelo cognitivo híbrido y original cuyas aportaciones principales son: la integración de teorías multi-disciplinares sobre la cognición (psicológicas, neurológicas,...

An attractive question which still remains on Intelligent Systems reseach field is how can we build autonomous agents whose internal cognition process can be self-configured over time? Our paper proposes a self-organized model for decision making, which is a robust evolutionary extension of typical Behaviors Network model. Given an initial set of m...

El aprendizaje de las matemáticas básicas en los primeros años de escolaridad es un punto neurálgico para la posterior adquisición de la lógica y razonamiento matemático avanzado. Un problema real con este tipo de aprendizaje es la ausencia casi total de personalización en la enseñanza. El objetivo de este libro es proponer un enfoque basado en téc...

For autonomous agents the problem of deciding what to do next becomes increasingly complex when acting in unpredictable and dynamic environments while pursuing multiple and possibly conflicting goals. One of the most relevant behavior-based models that tries to deal with this problem is the behavior network model proposed by Maes. This model propos...

Managing and arbitrating behaviours, processes and components in multilayered cognitive architectures when a huge amount of environmental variables are changing continuously with increasing complexity, ensue in a very comprehensive task. The presented framework proposes an hybrid cognitive architecture that relies on subsumption theory and includes...

Integrating different kinds of micro-theories of cognition in intelligent systems when a huge amount of variables are changing continuously, with increasing complexity, is a very exhaustive and complicated task. Our approach proposes a hybrid cognitive architecture that relies on the integration of emergent and cognitivist approaches using evolutio...

Incorporating different kinds of micro-theories of cognition and modulating several mechanisms to unify all the recommended actions and outputs of an intelligent system when a huge amount of environmental variables are changing continuously with increasing complexity, may become a very comprehensive task. The presented framework proposes an hybrid...

Managing and arbitrating behaviours, processes and components in multilayered cognitive architectures when a huge amount of environmental variables are changing continuously with increasing complexity, ensue in a very comprehensive task. The presented framework proposes an hybrid cognitive architecture that relies on subsumption theory and includes...

In this work, a hybrid, self-configurable, multilayered and evolutionary architecture for cognitive agents is developed. Each layer of the subsumption architecture is modeled by one different Machine Learning System MLS based on bio-inspired techniques. In this research an evolutionary mechanism supported on Gene Expression Programming to self-conf...

In this work, an hybrid, self-configurable, multilayered and evolutionary subsumption architecture for cognitive agents is developed. Each layer of the multilayered architecture is modeled by one different Machine Learning System (MLS) based on bio-inspired techniques such as Extended Classifier Systems (XCS), Artificial Immune Systems (AIS), Neuro...

Los animales artificiales son agentes inteligentes de software y/o hardware que demuestran un comportamiento similar al de los animales reales. Para esto deben contar con un mecanismo de aprendizaje que les permita adquirir nueva informaci6n mientras interactuan con su entorno, de forma que puedan utilizarla para mejorar su medida de desempe- fio....

En el campo de estudio de los Agentes Autónomos Inteligentes, uno de los retos más complejos de lograr es la simulación de los procesos cognitivos. Generalmente, la meta de integrar diversas micro-teorías en un solo modelo cognitivo que sea capaz de procesar ingentes cantidades de variables, las cuales cambian continuamente con una complejidad incr...