Top Research Papers on AI Agents

This essay concludes that until a Strong AI application can be demonstrated, the issue of legal agency of electronic agents ought not to detain the development of technology and of the law in this space.

This research effort sought to explore options to improve upon the wargaming framework infrastructure and to investigate opportunities to improve artificial intelligence (AI) agent behavior.

The real foundation of all sociality (cooperation, competition, groups, organisation, etc.) is the individual social action and mind, and cognition, communication and agreement are not enough for modelling and implementing cooperation: emergent pre-cognitive structures and constraints should be formalised, and emergent forms of cooperation are needed also among planning and deliberative agents.

The intuitive application of the respondeat superior doctrine provides the AI industry with a much-needed underlying liability regime which will enable it to continue to evolve in the years to come, and its victim to receive remedy once accidents occur.

This book is about artificial intelligence, a field built on centuries of thought, which has been a recognized discipline for over 60 years and can help understand current and future work in AI and equip you to contribute to the discipline yourself.

It is extremely unlikely that true AGI can be developed in the current algorithmic framework of AI research, and discussions about the proper development and deployment of algorithmic tools should be shaped around the dangers and opportunities of current narrow AI, not the extremely unlikely prospect of the emergence of true agency in artificial systems.

The purpose here is to introduce a few of the basic ideas behind AI, and to try and offer a means by which people can come to grips with the current state of the art in the field.

This paper deals with the intersection of AI and virtual worlds, focusing on AI agents and exploring the potential implications toward the human-level AI.

ThePolycraft World AI Lab (PAL), a task simulator with an API based on the Minecraft mod Polycraft World, is presented, a versatile and extensible AI evaluation platform with a low barrier to entry for AI researchers to utilize.

This chapter presents the current state-of-the-art in the field of intelligent agents, focusing on the role of AI planning techniques.

This perspective paper discusses the development of a personal AI agent, focusing on its architecture and requirements, and exemplifies how such an AI agent could work to assist researchers in materials sciences.

The results showed that the elements of the artificial intelligence avatar consist of four elements: 1) Nonverbal, 2) Verbal, 3) Appearance characteristics, and 4) Machine Learning.

This paper focuses on AI agents along with exploring the progress towards super intelligent AI and the roles played by artificial intelligence and virtual worlds in its development.

This paper suggests an idea to build such an intelligent agent that attempts to take the right decision in the new environment and shows the simulation of intelligent agent to avoid obstacle in new environment.

This paper tackles three misconceptions regarding discussions of the legal responsibility of artificially intelligent entities: these are that they (a) cannot be held legally responsible for their actions, because they do not have the prerequisite characteristics to be ‘real agents’ and therefore cannot ‘really’ act. (b) should not be held legally responsible for their actions, because they do not have the prerequisite characteristics to be ‘real agents’ and therefore cannot ‘really’ act. (c) should not be held legally responsible for their actions, because to do so would allow other (human...

A novel cyber intelligence solution is proposed, employing four semantic agents that interact autonomously to acquire crucial cyber intelligence pertaining to any given country, using a combination of techniques, including a convolutional neural network (CNN), sentiment analysis, exponential smoothing, latent Dirichlet allocation, and term frequency-inverse document frequency (TF-IDF).

The AI-assisted phone calls effectively identified the patients requiring further support, saved clinician time by monitoring less ailing patients remotely, and enabled them to spend more time on critically ill patients, thus ensuring that service and supply resources could be directed to those at greatest need.

A way to develop a class of AI systems, the Disruptive Interjector, which observe what a human is doing, then interject with suggestions that aid in idea generation or problem solving in a human-AI (H-AI) team; something that goes beyond current creativity support systems.

Healthcare professionals face complex ethical dilemmas in clinical settings in cases involving end-of-life care, informed consent, and surrogate decision-making. These nuanced situations often lead to moral distress among care providers. This paper introduces the Bioethics Artificial Intelligence Advisory (BAIA) framework, a novel and innovative approach that leverages artificial intelligence (AI) to support clinical ethical decision-making. The BAIA framework integrates multiple bioethical approaches, including principlism, casuistry, and narrative ethics, with advanced AI capabilities to pro...

This paper provides a comprehensive guide to assessing agent performance by examining key metrics such as accuracy, response time, and user satisfaction, and discussing practical methods for evaluation.

An interactive virtual tour based on Android with a first-person shooter approach to introduce the Adisutjipto Institute of Aerospace Technology (ITD Adisutjipto) virtually and is effective and feasible to use, with a user satisfaction rate reaching 87.72%.

The prototype visualizations developed to support the use case of a mission planner and an AI agent trainer include training results charts, heat map visualizations of agent paths, weight matrix visualizations, and ablation testing graphs.

The creation and potential of virtual characters in elementary classrooms, combined with biometrics and facial emotional recognition, which in this study has impacted student learning and offered support to the teacher.

An AI Agent framework named SOP-GPT is proposed which has integrated the concept of Standard Operating Procedures (SOP) from human workflow into AI Agents and the quality of generation was enhanced to meet the expectations of human work requirements.

This paper reviews the current state of the art in the research concerning the development of autonomous artificial intelligent agents and focuses, in particular, on the importance of autonomous embodied agents as support for genuine artificial intelligence.

A behaviours production system capable of reproducing a high number of properties of adaptive behaviour and of exhibiting emergent lower cognition and a simple model for social action is presented, obtaining emergent complex social processes from simple interactions of imitation and induction of behaviours in agents.

A rule-based market-maker, built in with multiple objectives, including maintaining a fair and orderly market, maximizing profit and minimizing inventory risk, is constructed and tested on historical transaction data and an adaptive market-makers is modeled in the framework of reinforcement learning.

The underpinnings for the architecture design of wireless multi-agent generative artificial intelligence systems at the network level and the agent level are established, and the wireless technologies that are envisioned to play a key role in enabling on-device LLM are identified.

A comparative discussion about two recent papers about assistive robots that can override commands and how they together create a more comprehensive framework for assistive robots that can override commands is provided.

The study demonstrates that the element of cuteness in AI agents plays a crucial role in shaping perceptions of benevolence trustworthiness, as well as fostering users' attachment to AI agents.

This survey thoroughly explores the foundational concepts, unique characteristics, and core methodologies driving the development of Agentic AI, and outlines a framework for safely and effectively integrating Agentic AI into society.

This study explores the ability of pre-trained language models to generate human-like responses to dialogues about physics by having ChatGTP, the pre-eminent language model in 2023, work through representative assessment content of an actual calculus-based physics course and grading the responses in the same way human responses would be graded.

Based on a dataset collected from 408 virtual assistant users from the US, this research develops and tests a model that can explain how AISA-enabled service influences subjective well-being through the mediating effect of PSR and indicates significant gender and AISA experience differences in the PSR effect on subjectiveWell-being.

A focus on cost in addition to accuracy motivates the new goal of jointly optimizing the two metrics, and design and implement one such optimization, showing its potential to greatly reduce cost while maintaining accuracy.

This review looks at some of the central relationships between artificial intelligence, psychology, and economics through the lens of information theory, specifically focusing on formal models of decision-theory.

A Hyper-Automated AI framework with Generative AI agents for sustainable smart cities to provide a validated pathway for university cities of the future to take up the role of prototypes that deliver evidence-based guidelines for the development and management of sustainable smart cities.

Three categories of measures to increase visibility into AI agents are assessed: agent identifiers, real-time monitoring, and activity logging that apply across a spectrum of centralized through decentralized deployment contexts, accounting for various actors in the supply chain including hardware and software service providers.

Artificial Intelligence (AI) technology can be found nearly everywhere, however, developing and controlling this technology is generally limited to large companies or those with extensive training in computer science.

Evidence is offered that AI agents can develop trusting and cooperative behaviors purely from an interactive trial-and-error learning process and constitutes a first step to build multiagent-based decision support systems in which interacting artificial agents are capable of leveraging social intelligence to achieve better outcomes collectively.

The results show that the proposed behavioural representation has better performance in extracting IA's situational awareness compared to the baseline method, which is significant to enhance human comprehension on IA so their trust in IA can be calibrated.

This study takes a look at the many topologies configurations of AC inverters and DC converters that are employed in the installation of fuel cells for autonomous and portable.

The demonstrated accuracy, efficiency, and objectivity show great potential for improving candidate selection, aligning individual skills with organizational goals, and ultimately enhancing the recruitment process.

A holistic, ethical, and epistemic analysis of CAI adoption is proposed and it is argued that CAI cannot be considered as an equal partner in a conversation as is the case with a human therapist and should be restricted to specific functions.

This research paper has discussed the problems mentioned above using the dataset provided by the NeurIPS 2022 IGLU Challenge which is a labeled dataset.

This thesis introduces procedurally generated new data to test VQA agents and other visual Al models on using Spatial IQ Generative Dataset (SIQGD) and 3D models along with a Blender3D extension.

This paper explains the reason by introducing service context and provides new insights into previous inconsistent evidence regarding anthropomorphic design’s influence on customers’ willingness to use AI service agents.

This paper proposes Architecture of chatbot system designed for college purpose, which students and teachers can access and use chatbot system anywhere and anytime to get required information.

It is suggested that preparedness for a future dominated by AI is essential, as generative AI technologies have the potential to profoundly impact teaching and learning methods, and necessitate new ways of thinking.

This chapter presents the current state-of-the-art in the field of intelligent agents, focusing on the role of AI planning techniques, and presents different AI planning methodologies implemented in intelligent agents applications.

The working hypothesis of this position paper is that the road to the next generation of autonomous robotic agents with cognitive capabilities requires a fully brain-inspired, embodied cognitive approach that avoids the trap of mind-body dualism and aims at the full integration of Bodyware and Cogniware.