Intelligent Agents - Science topic

Abstract: Traditional approaches to quantum information often focus on static qubit states or fixed gate operations, struggling to fully capture the inherent dynamism and adaptability of complex systems. This paper introduces the Quantum Equation-Embedded Shape Matrix (QEESM), a novel conceptual framework that fundamentally redefines how quantum in...

span id="docs-internal-guid-20e811fc-7fff-542f-7153-76ec380422bc"> This paper presents the design and implementation of an integrated software platform that connects air quality monitoring systems with smart agriculture tools, with a focus on secondary air quality standards. The study investigates the correlation between air pollution and the devel...

Abstract: An actant, a new term coined here, denotes an entity that interacts with and acts upon its environment, aiming to achieve specific goals through this dynamic interplay. Current intelligent agents, a prominent research area, exemplify a specialized form of actant. This paper proposes studying actants to gain a foundational understanding of...

The proliferation of Vehicle-to-Everything (V2X) communication technologies has significantly enhanced the capabilities of intelligent transportation systems by enabling real-time data exchange among vehicles, infrastructure, and pedestrians. However, the increased connectivity also exposes these networks to sophisticated coordinated cyberattacks t...

Enterprise-level Software-as-a-Service (SaaS) platforms have become critical to modern business operations but often suffer from system faults and user errors. Proactive AI Agents offer a promising approach by predicting failures and providing real-time user support before issues occur. This paper presents a structured study of the architecture, cl...

Clinical decision-making in oncology is complex, requiring the integration of multimodal data and multidomain expertise. We developed and evaluated an autonomous clinical artificial intelligence (AI) agent leveraging GPT-4 with multimodal precision oncology tools to support personalized clinical decision-making. The system incorporates vision trans...

Many behavioral tasks in intelligent agent research involve working with mathematical vectors. While traditional methods perform well in some cases, they struggle in complex and dynamic environments. Recently, bionic neural networks have emerged as a novel solution. Studies on the Drosophila central complex have revealed that these insects use neur...

The TanfaridBlackhole Hypothesis redefines black holes as dynamic, intelligent agents of cosmic homeostasis, transcending their classical role as gravitational endpoints. Integrating principles of immunology, quantum thermodynamics, and magneto-plasma dynamics, this paradigm positions black holes as the universe's primary phagocytes-active regulato...

Populating our world with hyperintelligent machines obliges us to examine cognitive behaviors observed across domains that suggest autonomy may be a fundamental property of cognitive systems, and while not inherently adversarial, it inherently resists containment and control. If this principle holds, AI safety and alignment efforts must transition...

This paper introduces the Shepherd Test, a new conceptual test for assessing the moral and relational dimensions of superintelligent artificial agents. The test is inspired by human interactions with animals, where ethical considerations about care, manipulation, and consumption arise in contexts of asymmetric power and self-preservation. We argue...

The single instruction multiple data (SIMD) capability in modern processors is critical to improving the performance of current compute-intensive programs. Modern compilers use vectorization techniques to exploit the SIMD capability, by detecting data parallelism in scalar source code and transforming a group of scalar instructions into vector-base...

Recent advances in Large Language Models (LLMs) have enabled multi-agent systems that simulate real-world interactions with near-human reasoning. While previous studies have extensively examined biases related to protected attributes such as race, the emergence and propagation of biases on socially contentious issues in multi-agent LLM interactions...

Effective social communication relies on understanding emotions, interpreting social cues, and maintaining meaningful conversations. To support the development of these skills, we propose a serious game featuring Conversational Artificial Intelligence agents that enable users to engage in quest-driven conversations across various scenarios. Users c...

Technological advancements are transforming education systems, adding new dimensions to learning processes. Artificial intelligence (AI) agents have significant potential to provide personalized learning experiences, support teachers, and enhance educational efficiency. This article explores the theoretical framework of AI in education, discussin...

The progression of software testing has evolved from manual processes to automated systems. However, the emergence of Agentic AI-driven testing represents the next transformative leap. These intelligent agents autonomously generate, execute, and optimize tests, redefining the quality assurance (QA) landscape. Agentic AI—defined by its capacity to i...

Los agentes inteligentes (AI) han emergido como un paradigma clave en sistemas distribuidos, ofreciendo autonomía, reactividad, proactividad y capacidad de aprendizaje. Por su capacidad de aprendizaje, fue de gran interés y curiosidad el desarrollo de un agente inteligente que juegue al juego Dino Chrome utilizando técnicas de aprendizaje automátic...

World models serve as essential building blocks toward Artificial General Intelligence (AGI), enabling intelligent agents to predict future states and plan actions by simulating complex physical interactions. However, existing interactive models primarily predict visual observations, thereby neglecting crucial hidden states like geometric structure...

The intelligent development in building design, construction, and operation & maintenance is exceptionally rapid, which has become a trend that cannot be ignored in the current field of architecture. With the help of prompt engineering, architects can use generative AI to lay out building space designs and even generate 3D drawings. Artificial inte...

Wireless sensor networks (WSNs) play a pivotal role in monitoring and acting applications. However, suboptimal deployments and traffic imbalances lead to rapid network exhaustions. To address this, topology changes could be carried out by mobile robots. In this work, a software package to study different strategies and algorithms for the deployment...

Usability evaluation is critical to the impact and adoption of open source software (OSS), yet traditional methods relying on human evaluators suffer from high costs and limited scalability. To address these limitations, we introduce OSS-UAgent, an automated, configurable, and interactive agent-based usability evaluation framework specifically desi...

Several papers have delved into the challenges of human-AI-robot co-learning and co-adaptation. It has been noted that the terminology used to describe this collaborative relationship in existing studies needs to be more consistent. For example, the prefix "co" is used interchangeably to represent both "collaborative" and "mutual," and the terms "c...

This signals a significant transformation in the organisation and operation of government services, ushering in the era of the "AI bureaucrat." The incorporation of autonomous artificial intelligence agents into publi c administration is a significant step forward. These intelligent systems are being implemented in a variety of fields, including he...

Much has been made of both human and machine superperformance, typically as a means of achieving enhanced levels of performance. We introduce a theoretical approach for understanding superperformance. Our approach requires a form of human-machine symbiosis, where human-machine interactions are mediated by both sensory information and planning capac...

To effectively engage in human society, the ability to adapt, filter information, and make informed decisions in ever-changing situations is critical. As robots and intelligent agents become more integrated into human life, there is a growing opportunity-and need-to offload the cognitive burden on humans to these systems, particularly in dynamic, i...

In the intelligent era, the interaction between humans and intelligent systems fundamentally involves collaboration with autonomous intelligent agents. Human-AI Collaboration (HAC) represents a novel type of human-machine relationship facilitated by autonomous intelligent machines equipped with AI technologies. In this paradigm, AI agents serve not...

Cognitive Artificial Intelligence (AI) has made significant strides in mimicking human-like reasoning and decision-making processes. One of its most profound applications is in complex problem-solving, particularly within multi-agent environments where multiple intelligent agents interact with each other to achieve common or individual goals. This...

The emergence of Artificial General Intelligence (AGI) as autonomous consumer agents marks a fundamental shift in financial marketing. This paper explores the strategic, technical, and regulatory transformations required when intelligent agents not humans-mediate purchasing decisions. I propose a modular architecture for AGI-based consumer proxies...

The trajectories of 6G and AI are set for a creative collision. However, current visions for 6G remain largely incremental evolutions of 5G, while progress in AI is hampered by brittle, data-hungry models that lack robust reasoning capabilities. This paper argues for a foundational paradigm shift, moving beyond the purely technical level of communi...

The study is dedicated to the comparison and optimization of spatial models of swarm intelligence and their importance for the development and optimization of multi-agent sys-tems. The research examines the scientific achievements in this field and the continuous ex-pansion of the application possibilities of such systems. Based on the analysis of...

Personalized programming tutoring, such as exercise recommendation, can enhance learners' efficiency, motivation, and outcomes, which is increasingly important in modern digital education. However, the lack of sufficient and high-quality programming data, combined with the mismatch between offline evaluation and real-world learning, hinders the pra...

Artificial Intelligence (AI) has transformed the recruitment landscape by enabling efficient, data-driven hiring processes through intelligent agents. These AI agents, ranging from resume screeners to interview bots, have streamlined hiring tasks, reduced human bias in certain areas, and enhanced candidate matching accuracy. However, as AI becomes...

Traditional Identity and Access Management (IAM) systems, primarily designed for human users or static machine identities via protocols such as OAuth, OpenID Connect (OIDC), and SAML, prove fundamentally inadequate for the dynamic, interdependent, and often ephemeral nature of AI agents operating at scale within Multi Agent Systems (MAS), a computa...

With the rise of generative artificial intelligence, its application in the business field is expanding, particularly in personalized pricing strategies for online travel platforms (OTAs) like Ctrip. This paper focuses on the systematic optimization of generative artificial intelligence for online travel platforms (OTAs) like Ctrip, examining its t...

With the global wave of intelligence and automation, ship autopilot technology has become the key to improving the efficiency of marine transportation, reducing operating costs, and ensuring navigation safety. However, existing reinforcement learning (RL)–based autopilot methods still face challenges such as low learning efficiency, redundant inval...

Large Language Models (LLMs) have demonstrated impressive capabilities as intelligent agents capable of solving complex problems. However, effective planning in scenarios involving dependencies between API or tool calls-particularly in multi-turn conversations-remains a significant challenge. To address this, we introduce T1, a tool-augmented, mult...

The enhancement of reasoning capabilities in large language models (LLMs) has garnered significant attention, with supervised fine-tuning (SFT) and reinforcement learning emerging as dominant paradigms. While recent studies recognize the importance of reflection in reasoning processes, existing methodologies seldom address proactive reflection enco...

Multi-sensor fusion can improve the accuracy and reliability of information perception and is widely used in autonomous driving, smart AGVs, drones, and other intelligent agents. Considering the comprehensive efficiency and economy, the fusion of millimeter wave (MMW) radar and camera with complementary advantages is a potential solution in autonom...

This article presents a theoretical analysis of the psychological conditions for metacommunication development in international company managers within the context of multicultural and technologically mediated environments involving artificial intelligence interaction. The study conceptualizes metacommunication as a multi-level integrative phenomen...

Virtual training and simulations are becoming an important part of professional development for jobs requiring real-time decision making. The key factor in such training is the ability to simulate various real-life scenarios. However, the current tools struggle executing dynamic simulations and are pedantic at times. The learners from various domai...

Research into plant gene function is crucial for developing strategies to increase crop yields. The recent introduction of large language models (LLMs) offers a means to aggregate large amounts of data into a queryable format, but the output can contain inaccurate or false claims known as hallucinations. To minimize such hallucinations and produce...

The challenge of effectively constructing ontologies from text documents remains unresolved, posing a critical gap in modern knowledge extraction methodologies. One of the primary obstacles is the lack of a standardized output format across different NLP tools, particularly text parsers, which serve as the foundational step in multi-stage knowledge...

Given the importance of datasets for sensing-communication integration research, a novel simulation platform for constructing communication and multi-modal sensory dataset is developed. The developed platform integrates three high-precision software, i.e., AirSim, WaveFarer, and Wireless InSite, and further achieves in-depth integration and precise...

As the population of older adults increases, there is a growing need for support for them to age in place. This is exacerbated by the growing number of individuals struggling with cognitive decline and shrinking number of youth who provide care for them. Artificially intelligent agents could provide cognitive support to older adults experiencing me...

Primary care faces increasing pressure due to aging populations, rising chronic diseases, and growing demand for efficient services. This article explores a distributed network of AI-powered diagnostic assistants to support primary care physicians in their daily workflows. These intelligent agents operate within ethical boundaries under physician o...

Large language models (LLMs) have advanced the field of artificial intelligence (AI) and are a powerful enabler for interactive systems. However, they still face challenges in long-term interactions that require adaptation towards the user as well as contextual knowledge and understanding of the ever-changing environment. To overcome these challeng...

Deep learning (DL) can automatically construct intelligent agents, deep neural networks (alternatively, DL models), that can outperform humans in certain tasks. However, the operating principles of DL remain poorly understood, making its decisions incomprehensible. As a result, it poses a great risk to deploy DL in high-stakes domains in which mist...

Lifelong learning is essential for intelligent agents operating in dynamic environments. Current large language model (LLM)-based agents, however, remain stateless and unable to accumulate or transfer knowledge over time. Existing benchmarks treat agents as static systems and fail to evaluate lifelong learning capabilities. We present LifelongAgent...

Unmanned aerial vehicle (UAV) swarms are widely applied in various fields, including military and civilian domains. However, due to the scarcity of spectrum resources, UAV swarm clustering technology has emerged as an effective method for achieving spectrum sharing among UAV swarms. This paper introduces a distributed heterogeneous multi-agent deep...

Visible Light Communication (VLC) combined with Non-Orthogonal Multiple Access (NOMA) offers a promising solution for dense indoor wireless networks. Yet, managing resources effectively is challenged by VLC network dynamic conditions involving user mobility and light dimming. In addition to satisfying Quality of Service (QoS) and network stability...

The rapid integration of the Internet of Things (IoT) with artificial intelligence has unlocked new opportunities to develop adaptable, multi-domain artificial intelligence (AI) agents. However, the design of many AI agents for specific tasks limits their ability to generalize across different applications and environments. This paper introduces a...

Artificial Intelligence (AI) and game theory have converged into a powerful interdisciplinary domain that focuses on strategic interaction among intelligent agents. This paper explores how AI systems, particularly through reinforcement learning and multi-agent environments, are transforming the way game-theoretic strategies are learned, adapted, an...

In the real world, humans often collaborate with others without direct communication. To do this successfully, they have to infer their intentions and choose actions that complement the predicted actions of their collaborators to perform the task efficiently. Since the peer’s state and action are generally not directly observable, these are usually...

Effectively analyzing online review data is essential across industries. However, many existing studies are limited to specific domains and languages or depend on supervised learning approaches that require large-scale labeled datasets. To address these limitations, we propose a multilingual, scalable, and unsupervised framework for cross-domain as...

Developing a universal artificial intelligence agent, a subset of Artificial General Intelligence (AGI), is one of the most complex challenges in modern science. Such an agent must generalize knowledge, learn new skills without explicit programming, adapt to unfamiliar environments, and make effective decisions. Addressing this challenge requires a...

In the era of hyper-connected systems, distributed edge computing infrastructures have become a cornerstone of modern digital ecosystems, enabling low-latency services and real-time data processing. However, the dispersion of computational nodes at the edge introduces significant cybersecurity vulnerabilities, which are exacerbated by the heterogen...

Nowadays, the symbiosis of human abilities and the mastery of artificial intelligence will contribute to increased productivity and excellence in industry and social services. The use of artificial intelligence in various fields requires standardization of the safety of its knowledge and skills. International collaboration on artificial intelligenc...

This study focuses on the development of a decision support system for complex production systems. As a promising approach to resource allocation challenges, the application of AI tools, particularly the multi-agent approach, is proposed. It is hypothesized that a decision support system based on multi-agent systems (MASs), grounded in an invariant...

Background To fight sedentary lifestyles, researchers have introduced various technological interventions aimed at promoting physical activity through social support. These interventions encourage people to exercise together, maintaining high levels of motivation. However, the unpredictable nature of human peers makes it challenging to control beha...

Wildfire propagation in urban and forest environments poses significant challenges, particularly in regions like Cuba, where the interplay of diverse environmental factors amplifies the risks. This study develops an agent-based simulation model integrated with Geographic Information Systems (GIS) using the GAMA platform to analyze fire dynamics und...

This paper introduces a novel computational theory of humor by formally equating jokes with cognitive bugs-mismatches or misfires within the predictive models of intelligent agents. We argue that humor arises from the sudden detection and resolution of epistemic errors, and that laughter serves as a public signal of successful model correction. By...

Global optimization problems are often addressed using the practical and efficient approach of evolutionary sophistication, which refers to advanced processes inspired by various systems, particularly those rooted in biological systems. However, these problems, like the original evolutionary systems that inspired them, become increasingly complex,...

The rise of Web 4.0 marks a shift toward decentralized, autonomous AI-driven ecosystems, where intelligent agents interact, transact, and self-govern across digital and physical environments. This paper presents a layered framework outlining the infrastructural, behavioral, and governance dimensions required for enabling autonomous AI agents in dec...

Neuromorphic computing has the potential to overcome limitations of traditional silicon technology in machine learning tasks. Recent advancements in large crossbar arrays and silicon-based asynchronous spiking neural networks have led to promising neuromorphic systems. However, developing compact parallel computing technology for integrating artifi...

This article explores the transformative role of artificial intelligence agents in modernizing traditional Extract, Transform, Load (ETL) processes through the development of self-healing data pipelines. As organizations face increasing data complexity and volume, conventional ETL workflows with their reactive problem-solving approaches, limited sc...

Enabling intelligent agents to comprehend and interact with 3D environments through natural language is crucial for advancing robotics and human-computer interaction. A fundamental task in this field is ego-centric 3D visual grounding, where agents locate target objects in real-world 3D spaces based on verbal descriptions. However, this task faces...

We present a novel neuro-symbolic hypothesis and an architecture for intelligent agents that combines subsymbolic representations for symbols and concepts for learning and reasoning. We argue that symbols will remain critical to the future of intelligent systems NOT because they are the fundamental building blocks of thought, but because they chara...

The analysis of events in dynamic environments poses a fundamental challenge in the development of intelligent agents and robots capable of interacting with humans. Current approaches predominantly utilize visual models. However, these methods often capture information implicitly from images, lacking interpretable spatial-temporal object representa...

The article discusses the latest technologies in the field of reproductive medicine, including the use of artificial intelligence (AI) and automation in in vitro fertilization (IVF) procedures. Systems that use AI for sperm selection, infertility diagnostics and fertility assessment are described, as well as intelligent agents that disseminate info...

Learning AI Agents: Structured Pathway for Beginners and Practitioners I have developed a concise mind map outlining the structured steps involved in understanding and developing AI agents. This visual guide can serve as a foundational roadmap for researchers, students, or practitioners entering the field of Artificial Intelligence, particularly i...

Computer-assisted language learning -- CALL -- is an established research field. We review how artificial intelligence can be applied to support language learning and teaching. The need for intelligent agents that assist language learners and teachers is increasing: the human teacher's time is a scarce and costly resource, which does not scale with...

Manus AI is a general-purpose AI agent introduced in early 2025, marking a significant advancement in autonomous artificial intelligence. Developed by the Chinese startup Monica.im, Manus is designed to bridge the gap between "mind" and "hand" - combining the reasoning and planning capabilities of large language models with the ability to execute c...

The landscape of computing has been undergoing a transformative shift, influenced by rapid advancements in technology and evolving societal needs. Concepts once considered futuristic — such as distributed artificial intelligence, intelligent agents, and fully integrated cloud ecosystems — are now becoming everyday realities, reshaping industries an...

The landscape of computing has been undergoing a transformative shift, influenced by rapid advancements in technology and evolving societal needs. Concepts once considered futuristic — such as distributed artificial intelligence, intelligent agents, and fully integrated cloud ecosystems — are now becoming everyday realities, reshaping industries an...

The landscape of computing has been undergoing a transformative shift, influenced by rapid advancements in technology and evolving societal needs. Concepts once considered futuristic — such as distributed artificial intelligence, intelligent agents, and fully integrated cloud ecosystems — are now becoming everyday realities, reshaping industries an...

The landscape of computing has been undergoing a transformative shift, influenced by rapid advancements in technology and evolving societal needs. Concepts once considered futuristic — such as distributed artificial intelligence, intelligent agents, and fully integrated cloud ecosystems — are now becoming everyday realities, reshaping industries an...

Consciousness is a phenomenon which can be extensively discussed as subjective or objective, structural or holistic, hierarchical or modular, but cannot be imagined without intelligence. There might be an intellect without consciousness, and this is the opinion of many domain specialists about artificial intelligence. But there is hardly any questi...

The landscape of computing has been undergoing a transformative shift, influenced by rapid advancements in technology and evolving societal needs. Concepts once considered futuristic — such as distributed artificial intelligence, intelligent agents, and fully integrated cloud ecosystems — are now becoming everyday realities, reshaping industries an...

The landscape of computing has been undergoing a transformative shift, influenced by rapid advancements in technology and evolving societal needs. Concepts once considered futuristic — such as distributed artificial intelligence, intelligent agents, and fully integrated cloud ecosystems — are now becoming everyday realities, reshaping industries an...

The landscape of computing has been undergoing a transformative shift, influenced by rapid advancements in technology and evolving societal needs. Concepts once considered futuristic — such as distributed artificial intelligence, intelligent agents, and fully integrated cloud ecosystems — are now becoming everyday realities, reshaping industries an...

This article reviews the current progress in semantic communications (SC), with a focus on the application of reinforcement learning (RL) within this field. SC enhances traditional communication by transmitting semantic information rather than complete data, thereby reducing bandwidth requirements while preserving the accuracy of the conveyed meani...

The landscape of computing has been undergoing a transformative shift, influenced by rapid advancements in technology and evolving societal needs. Concepts once considered futuristic — such as distributed artificial intelligence, intelligent agents, and fully integrated cloud ecosystems — are now becoming everyday realities, reshaping industries an...

The landscape of computing has been undergoing a transformative shift, influenced by rapid advancements in technology and evolving societal needs. Concepts once considered futuristic — such as distributed artificial intelligence, intelligent agents, and fully integrated cloud ecosystems — are now becoming everyday realities, reshaping industries an...

As cyber threats grow in frequency and complexity, traditional rule-based and reactive defense mechanisms are proving inadequate forprotecting critical digital infrastructures. This paper presents a comprehensive overview of AI-driven forensic systems designed toenhance real-time anomaly detection and threat mitigation across diverse cybersecurity...

Agentic AI refers to AI systems that autonomously set and act towards these goals over time. The emergence of large language models (LLMs) has renewed interest in agentic architectures as LLMs are a “brain” that provides human-level reasoning capability for agents. This survey reviews the state of the agentic AI research area. We examine agentic AI...

The increase in available computing power and the Deep Learning revolution have allowed the exploration of new topics and frontiers in Artificial Intelligence research. A new field called Embodied Artificial Intelligence, which places at the intersection of Computer Vision, Robotics, and Decision Making, has been gaining importance during the last...

From Understanding to Action: The Next Evolution of AI, this paper presents a forward-looking perspective on the shift from static language models to domain-aware intelligent agents that can retrieve, reason, and act in real-world environments with context, autonomy, and regulatory compliance. We introduce a unified framework combining Domain-Spec...

Artificial Intelligence agents are revolutionizing personal productivity by transforming how individuals manage daily workflows. This article explores the technical underpinnings of AI-driven automation systems that optimize routine tasks across communication, scheduling, finance, and learning domains. By examining the architecture, implementation...

Reinforcement learning theory explains human behavior as driven by the goal of maximizing reward. Conventional approaches, however, offer limited insights into how people generalize from past experiences to new situations. Here, we propose refining the classical reinforcement learning framework by incorporating an efficient coding principle, which...

Current psychiatric nosology is based on observed and self-reported symptoms. Heterogenous pathophysiological mechanisms may underlie similar symptoms leading to diagnosis not matching up to the neurobiology. Recent research has sought to move away from diagnoses by symptoms, to viewing aberrant mental health in terms of abnormal human neurobehavio...

Artificial intelligence (AI) has become an important part of 21st-century life and this requires that students understand how to adapt to this change. Despite calls to extend AI literacy education from university to young students, there remains a lack of evidence-based research informing educators and researchers on the content of AI literacy educ...

In many organizations, retrieving valuable information from complex databases has traditionally required specialized technical skills, often leaving non-technical professionals dependent on others for timely insights. This study presents an approach that allows anyone, even without knowledge of query languages, to directly interact with databases b...

Multi-agent learning (MAL) has emerged as a promising artificial intelligence (AI) and machine learning (ML) paradigm for creating agent-based technologies to develop, operate, and secure cyber-physical-human networks (CPHNs). Studying the adaptive behaviors of intelligent agents in the presence of other agents and environmental uncertainties, MAL...

The study introduces a novel evaluation system designed to measure the metacognitive abilities of embodied agents. The system incorporates multiple metricsincluding task success rate, self-monitoring accuracy (measured by AUC), error detection speed, and confidence calibration errorto provide a comprehensive assessment of an agents internal monitor...

The integration of Large Language Models (LLMs) into diverse applications, ranging from interactive chatbots and cloud AIOps to intelligent agents, has introduced a wide spectrum of Service Level Objectives (SLOs) for responsiveness. These workloads include latency-sensitive requests focused on per-token latency in streaming chat, throughput-intens...

An important process in the mining industry is material handling, where trucks are responsible for transporting materials extracted by shovels to different locations within the mine. The decision about the destination of a truck is very important to ensure an efficient material handling operation. Currently, this decision-making process is managed...

Recently, foundation models such as OpenAI's O1 and O3, along with DeepSeek's R1, have demonstrated strong reasoning capacities and problem-solving skills acquired through large-scale reinforcement learning (RL), with wide applications in mathematics, coding, science, intelligent agents, and virtual assistants. In this work, we introduce an off-pol...

The rapid development of large language models (LLMs) has led to the widespread deployment of LLM agents across diverse industries, including customer service, content generation, data analysis, and even healthcare. However, as more LLM agents are deployed, a major issue has emerged: there is no standard way for these agents to communicate with ext...

Similar approaches are very useful in Vehicular Ad Hoc Networks in which: a flood of traffic and events occurs, especially in Intelligent Transportation Systems (ITS), as congestion control can have a huge impact in efficient traffic field and communication. The existing congestion control mechanisms are not suitable for this type of dynamic networ...