Related papers: Trust Modelling and Verification Using Event-B

Large language models (LLMs) have achieved impressive results in natural language understanding, yet their reasoning capabilities remain limited when operating as single agents. Multi-Agent Debate (MAD) has been proposed to address this…

Human-robot teams have the ability to perform better across various tasks than human-only and robot-only teams. However, such improvements cannot be realized without proper task allocation. Trust is an important factor in teaming…

One critical aspect of building human-centered, trustworthy artificial intelligence (AI) systems is maintaining calibrated trust: appropriate reliance on AI systems outperforms both overtrust (e.g., automation bias) and undertrust (e.g.,…

As large language models evolve from conversational assistants to autonomous agents, ensuring trustworthiness requires a fundamental shift from post-hoc evaluation to real-time action verification. Current frameworks like AgentBench…

Many decision-making processes have begun to incorporate an AI element, including prison sentence recommendations, college admissions, hiring, and mortgage approval. In all of these cases, AI models are being trained to help human decision…

As chatbots increasingly blur the boundary between automated systems and human conversation, the foundations of trust in these systems warrant closer examination. While regulatory and policy frameworks tend to define trust in normative…

The actions of intelligent agents, such as chatbots, recommender systems, and virtual assistants are typically not fully transparent to the user. Consequently, using such an agent involves the user exposing themselves to the risk that the…

There is a long history in game theory on the topic of Bayesian or "rational" learning, in which each player maintains beliefs over a set of alternative behaviours, or types, for the other players. This idea has gained increasing interest…

Machine learning systems have become popular in fields such as marketing, financing, or data mining. While they are highly accurate, complex machine learning systems pose challenges for engineers and users. Their inherent complexity makes…

We describe the steps of developing the MDMT (Multi-Dimensional Measure of Trust), an intuitive self-report measure of perceived trustworthiness of various agents (human, robot, animal). We summarize the evidence that led to the original…

One of the most challenging tasks in software specifications engineering for a multi-agent system is to ensure correctness. As these systems have high concurrency, often have dynamic environments, the formal specification and verification…

As AI models become ever more complex and intertwined in humans' daily lives, greater levels of interactivity of explainable AI (XAI) methods are needed. In this paper, we propose the use of belief change theory as a formal foundation for…

In this paper, we present a model of a trust-based recommendation system on a social network. The idea of the model is that agents use their social network to reach information and their trust relationships to filter it. We investigate how…

Stochastic multi-agent systems are a central modeling framework for autonomous controllers, communication protocols, and cyber-physical infrastructures. In many such systems, however, transition probabilities are only estimated from data…

While multi-agent systems (MAS) have demonstrated superior performance over single-agent approaches in complex reasoning tasks, they often suffer from significant computational inefficiencies. Existing frameworks typically deploy large…

System correctness is one of the most crucial and challenging objectives in software and hardware systems. With the increasing evolution of connected and distributed systems, ensuring their correctness requires the use of formal…

Artificial Intelligence (AI) techniques, particularly machine learning techniques, are rapidly transforming tactical operations by augmenting human decision-making capabilities. This paper explores AI-driven Human-Autonomy Teaming (HAT) as…

While trust in human-robot interaction is increasingly recognized as necessary for the implementation of social robots, our understanding of regulating trust in human-robot interaction is yet limited. In the current experiment, we evaluated…

In this study, a new ensemble approach for classifiers is introduced. A verification method for better error elimination is developed through the integration of multiple classifiers. A multi-agent system comprised of multiple classifiers is…

Multi-fidelity methods combine inexpensive low-fidelity simulations with costly but highfidelity simulations to produce an accurate model of a system of interest at minimal cost. They have proven useful in modeling physical systems and have…