Extended reality (XR) is well suited to support the situated learning of technical procedures. At the same time, AI-driven intelligent tutoring systems (ITS) can complement XR by providing adaptive pedagogical support. Many domains would benefit from this combination, especially when trainers, equipment, or team members are limited. We present a domain-agnostic XR-based ITS that integrates a training procedure representation (TPR), XR simulation, and an LLM-driven instructor. We demonstrate the tutor's use for tissue sample handling and engine repair, showing how it delivers adaptive feedback, collaborative roleplay, and dynamic scenario management to create realistic and pedagogically meaningful training experiences.

Social skills training targets behaviors necessary for success in social interactions. However, traditional classroom training for such skills is often insufficient to teach effective communication — one-to-one interaction in real-world scenarios is preferred to lecture-style information delivery. This paper introduces a framework that allows instructors to collaborate with large language models to dynamically design realistic scenarios for students to communicate. Our framework uses these scenarios to enable student rehearsal, provide immediate feedback and visualize performance for both students and instructors. Unlike traditional intelligent tutoring systems, instructors can easily co-create scenarios with a large language model without technical skills. Additionally, the system generates new scenario branches in real time when existing options don't fit the student's response.

This innovative practice WIP paper presents SABERR, a novel formative assessment designed to leverage errors as a learning resource in an artificial intelligence (AI) course. Previous research suggests that utilizing mistakes as learning tools enhances students' problem-solving abilities, metacognitive skills, and deepens their conceptual understanding across STEM fields. The intended outcomes of SABERR are supporting and enhancing students' learning by using their mistakes as resources to improve their awareness about their own knowledge and problem-solving strategies. The application design of the SABERR assessment unfolds in three structured phases which involve a reflective process where students are asked to articulate and explain the reasoning behind their initial errors. Our preliminary findings reveal that students initially struggled with error analysis and articulating knowledge gaps. However, a structured, step-by-step process significantly enhanced their error identification and correction abilities. The SABERR assessment approach significantly shifted student behavior towards prioritizing mastery of material, which was evidenced by increased engagement in class discussions and a reduction in academic dishonesty. Students reported improved ability to detect and correct errors, with 95% acknowledging enhanced understanding of AI concepts. However, this method also increased the workload for instructors and teaching assistants. Overall, 91% of students believed that a productive attitude towards mistakes would benefit their future careers, underscoring the effectiveness of SABERR in fostering a deeper, more analytical learning process among computer science students. The findings from our pilot study emphasize that the SABERR assessment approach not only enhances students' conceptual understanding and problem-solving capabilities but also promotes metacognitive skill development. By framing errors as learning tools, the approach encourages students to become active, reflective participants in their own learning processes. These findings also highlight the need for assessment approaches that enable both instructors and students to reframe errors as learning opportunities, thereby changing their perceptions.

Artificial intelligence (AI) and especially reinforcement learning (RL) have the potential to enable agents to learn and perform tasks autonomously with superhuman performance. However, we consider RL as fundamentally a Human-in-the-Loop (HITL) paradigm, even when an agent eventually performs its task autonomously. In cases where the reward function is challenging or impossible to define, HITL approaches are considered particularly advantageous. The application of Reinforcement Learning from Human Feedback (RLHF) in systems such as ChatGPT demonstrates the effectiveness of optimizing for user experience and integrating their feedback into the training loop. In HITL RL, human input is integrated during the agent’s learning process, allowing iterative updates and fine-tuning based on human feedback, thus enhancing the agent’s performance. Since the human is an essential part of this process, we argue that human-centric approaches are the key to successful RL, a fact that has not been adequately considered in the existing literature. This paper aims to inform readers about current explainability methods in HITL RL. It also shows how the application of explainable AI (xAI) and specific improvements to existing explainability approaches can enable a better human-agent interaction in HITL RL for all types of users, whether for lay people, domain experts, or machine learning specialists. Accounting for the workflow in HITL RL and based on software and machine learning methodologies, this article identifies four phases for human involvement for creating HITL RL systems: (1) Agent Development, (2) Agent Learning, (3) Agent Evaluation, and (4) Agent Deployment. We highlight human involvement, explanation requirements, new challenges, and goals for each phase. We furthermore identify low-risk, high-return opportunities for explainability research in HITL RL and present long-term research goals to advance the field. Finally, we propose a vision of human-robot collaboration that allows both parties to reach their full potential and cooperate effectively.

We propose an AI-based pilot trainer to help students learn how to fly aircraft. First, an AI agent uses behavioral cloning to learn flying maneuvers from qualified flight instructors. Later, the system uses the agent's decisions to detect errors made by students and provide feedback to help students correct their errors. This paper presents an instantiation of the pilot trainer. We focus on teaching straight and level flying maneuvers by automatically providing formative feedback to the human student.

Goal Recognition Design (GRD) problems identify the minimum number of environmental modifications aiming to force an interacting agent to reveal its goal as early as possible. Researchers proposed several extensions to the original model, some of them handling stochastic agent action outcomes. While this generalization is useful, it assumes optimal acting agents, which limits its applicability to more realistic scenarios. This paper presents the Suboptimal Stochastic GRD model, where we consider boundedly rational agents that, due to limited resources, might follow a suboptimal policy. Inspired by theories on human behavior asserting that humans are (close to) optimal when making perceptual decisions, we assume the chosen policy has at most m suboptimal actions. Our contribution includes (I) Extending the stochastic goal recognition design framework by supporting suboptimal agents in cases where an observer has either full or partial observability; (ii) Presenting methods to evaluate the ambiguity of the model under these assumptions; and (iii) Evaluating our approach on a range of benchmark applications.

We introduce Detection and Recognition of Airplane GOals with Navigational Visualization (DRAGON-V), a visualization system that uses probabilistic goal recognition to infer and display the most probable airport runway that a pilot is approaching. DRAGON-V is especially useful in cases of miscommunication, low visibility, or lack of airport familiarity which may result in a pilot deviating from the assigned taxiing route. The visualization system conveys relevant information, and updates according to the airplane's current geolocation. DRAGON-V aims to assist air traffic controllers in reducing incidents of runway incursions at airports.

Given an environment and a set of allowed modifications, the task of goal recognition design (GRD) is to select a valid set of modifications that minimizes the maximal number of steps an agent can take before its goal is revealed to an observer. This document presents an extension of GRD to the stochastic domain: the Stochastic Goal Recognition Design (S-GRD). The GRD framework aims to consider: (1) Stochastic agent action outcomes; (2) Partial observability of agent states and actions; and (3) Suboptimal agents. In this abstract we present the progress made towards the final objective as well as a timeline of projected conclusion.

Goal Recognition Design (GRD) problems involve identifying the best ways to modify the underlying environment that agents operate in, typically by making a subset of feasible actions infeasible, in such a way that agents are forced to reveal their goals as early as possible. The Stochastic GRD (S-GRD) model is an important extension that introduced stochasticity to the outcome of agent actions. Unfortunately, the worst-case distinctiveness (wcd) metric proposed for S-GRDs has a formal definition that is inconsistent with its intuitive definition, which is the maximal number of actions an agent can take, in the expectation, before its goal is revealed. In this paper, we make the following contributions: (1) We propose a new wcd metric, called all-goals wcd (wcdag), that remedies this inconsistency; (2) We introduce a new metric, called expected-case distinctiveness (ecd), that weighs the possible goals based on their importance; (3) We provide theoretical results comparing these different metrics as well as the complexity of computing them optimally; and (4) We describe new efficient algorithms to compute the wcdag and ecd values.