Ashok K. Goel

Xiao Jin, Rahul K. Dass, Ashok K. Goel

Intelligent tutoring systems excel at generating explanations but rarely provide principled diagnosis of where and why a learner is wrong. We introduce a misstep-aware coaching capability for Ivy, a neurosymbolic AI coach, built on a two-model architecture that augments a Task-Method-Knowledge (TMK) model with a new Pedagogical Model (PM) in the context of an online graduate AI course at Georgia Tech. The PM makes instructor diagnostic knowledge explicit and machine-readable by encoding, for each quiz question and incorrect response, the learner's underlying belief(a brief statement of the incorrect idea or missing knowledge), a TMK locus(the source of the misunderstanding), a misconception type and targeted scaffolding derived from the instructor's Q\&A key. Using quiz questions from the course, we demonstrate a proof-of-concept pipeline that detects and classifies learner errors and generates diagnosis-grounded scaffolding, moving Ivy beyond knowledge retrieval toward diagnostic misstep awareness, and enabling more precise, actionable feedback that supports conceptual change and advances adaptive learning systems in AI in education and the learning sciences.

Junsoo Park, Youssef Medhat, Htet Phyo Wai et al.

AI-augmented classrooms generate rich teacher and student feedback before graded outcomes become available, yet these signals can be difficult to translate into timely instructional decisions. We propose an interpretable decision layer: a transparent mechanism that ranks course topics requiring attention without using grades or post-hoc outcome labels. The approach combines three signals: student learning difficulty prevalence, disagreement between learner self-reports and observed difficulties, and unresolved teacher concerns. The output is a ranked set of topic priorities with per-topic decision records explaining each ranking. In one graduate CS course offering ($n=5$ instructor interviews; $n=279$ survey responses), prioritized topics aligned with instructor concerns (top-5 overlap 3/5; Spearman $ρ=0.80$) and student-reported topic difficulty ($ρ=0.46$, $p=.048$). Multi-signal integration also surfaced learners not identified through individual signal sources alone (AUC $=0.96$ vs. $0.91$ for gap prevalence alone). Reflective thinking, help-seeking, and self-efficacy provided additional evidence that student behavioral signals align with learning-related constructs. While preliminary, these findings suggest that transparent coordination mechanisms may help support human-AI co-agency when feedback is incomplete.

Natalia Theodora, Ploy Thajchayapong, Ashok K. Goel

The application of AI in education has evolved from monolithic intelligent tutoring systems to a diverse ecosystem of pedagogical agents, including conversational assistants, virtual coaches, and adaptive tutors. This shift requires a unified and scalable data architecture to manage the complex information feedback loops between human instructors, learners, and the varied AI agents. The design, development, and deployment of the data architecture in turn raises a critical issue of validation. This paper addresses this critical need by describing a practical validation strategy for a high-volume data pipeline developed as part of a data architecture for AI-augmented adult learning at the National AI Institute for Adult Learning and Online Education. Our approach involves a two-stage testing methodology to ensure both functional diversity and real-world scalability. First, the QA environment uses a blend of synthetic and real-world data to validate functional correctness across various event types produced from learner and agent interactions. Following this, the production environment successfully processed a total of over 2.7 million production requests across 21 successful runs carrying authentic event data from a large-scale online program. This validation process surfaced crucial insights into data privacy, a key challenge when handling varied data from multiple AI agent data sources. By outlining a replicable testing strategy for a unified data backbone, this research offers a clear framework for institutions and developers aiming to build and support their own heterogeneous suites of AI-powered learning tools. Keywords: Pedagogical Agents, Learning Ecosystems, Data Architecture, Validation, Scalability, Learning Analytics.

Qiaosi Wang, Ashok K. Goel

New developments are enabling AI systems to perceive, recognize, and respond with social cues based on inferences made from humans' explicit or implicit behavioral and verbal cues. These AI systems, equipped with an equivalent of human's Theory of Mind (ToM) capability, are currently serving as matchmakers on dating platforms, assisting student learning as teaching assistants, and enhancing productivity as work partners. They mark a new era in human-AI interaction (HAI) that diverges from traditional human-computer interaction (HCI), where computers are commonly seen as tools instead of social actors. Designing and understanding the human perceptions and experiences in this emerging HAI era becomes an urgent and critical issue for AI systems to fulfill human needs and mitigate risks across social contexts. In this paper, we posit the Mutual Theory of Mind (MToM) framework, inspired by our capability of ToM in human-human communications, to guide this new generation of HAI research by highlighting the iterative and mutual shaping nature of human-AI communication. We discuss the motivation of the MToM framework and its three key components that iteratively shape the human-AI communication in three stages. We then describe two empirical studies inspired by the MToM framework to demonstrate the power of MToM in guiding the design and understanding of human-AI communication. Finally, we discuss future research opportunities in human-AI interaction through the lens of MToM.

Sungeun An, Spencer Rugaber, Jennifer Hammock et al.

We described a study on the use of an online laboratory for self-directed learning by constructing and simulating conceptual models of ecological systems. In this study, we could observe only the modeling behaviors and outcomes; the learning goals and outcomes were unknown. We used machine learning techniques to analyze the modeling behaviors of 315 learners and 822 conceptual models they generated. We derive three main conclusions from the results. First, learners manifest three types of modeling behaviors: observation (simulation focused), construction (construction focused), and full exploration (model construction, evaluation and revision). Second, while observation was the most common behavior among all learners, construction without evaluation was more common for less engaged learners and full exploration occurred mostly for more engaged learners. Third, learners who explored the full cycle of model construction, evaluation and revision generated models of higher quality. These modeling behaviors provide insights into self-directed learning at large.

Pratyusha Maiti, Ashok K. Goel

Jill Watson, a virtual teaching assistant powered by LLMs, answers student questions and engages them in extended conversations on courseware provided by the instructors. In this paper, we analyze student interactions with Jill across multiple courses and colleges, focusing on the types and complexity of student questions based on Bloom's Revised Taxonomy and tool usage patterns. We find that, by supporting a wide range of cognitive demands, Jill encourages students to engage in sophisticated, higher-order cognitive questions. However, the frequency of usage varies significantly across deployments, and the types of questions asked depend on course-specific contexts. These findings pave the way for future work on AI-driven educational tools tailored to individual learning styles and course structure, potentially enhancing both the teaching and learning experience in classrooms.

Rahul K. Dass, Shubham Puri, Arpit Khandelwal et al.

Scalable AI tutoring for procedural skill learning requires structured knowledge representations, yet constructing these representations remains a labor-intensive bottleneck. This paper presents a human-in-the-loop text-to-model pipeline that uses large language models to transform instructional materials into schema-complete Task-Method-Knowledge models of procedural skills through ontology-constrained prompting and template-based generation. The approach automates structural scaffolding while preserving expert oversight for validating causal transitions and failure conditions. We apply the pipeline to instructional materials from a graduate-level online AI course, constructing 23 procedural skill models. AI-assisted authoring reduced expert modeling time by 50-70% while producing structurally valid and highly reproducible models under fixed-input conditions. We evaluate structural validity, semantic alignment, reproducibility, and refinement effort to characterize authoring scalability. Results indicate that AI-assisted text-to-model methods can substantially lower the cost of constructing structured procedural representations, making course-wide deployment of structured AI coaching systems practically feasible.

Junsoo Park, Youssef Medhat, Htet Phyo Wai et al.

We study how conditioning context shapes personalization behavior in a teacher-facing educational recommender system. We compare contextual conditioning based on the current student question with memory-based conditioning using persistent learner information. Using deviation correlation and paired statistical tests, we find that contextual recommendations exhibit stronger question-level responsiveness, while memory-based recommendations exhibit history-dependent behaviors, including learner-specific differentiation under identical input. Teacher-facing evaluation signals suggest these recommendations are interpretable and actionable. These results indicate that embedding-based similarity metrics capture responsiveness to the current question but do not characterize personalization grounded in learner history, motivating behavior-level diagnostics for studying conditioning effects.

Karan Taneja, Pratyusha Maiti, Sandeep Kakar et al.

Conversational AI agents often require extensive datasets for training that are not publicly released, are limited to social chit-chat or handling a specific domain, and may not be easily extended to accommodate the latest advances in AI technologies. This paper introduces Jill Watson, a conversational Virtual Teaching Assistant (VTA) leveraging the capabilities of ChatGPT. Jill Watson based on ChatGPT requires no prior training and uses a modular design to allow the integration of new APIs using a skill-based architecture inspired by XiaoIce. Jill Watson is also well-suited for intelligent textbooks as it can process and converse using multiple large documents. We exclusively utilize publicly available resources for reproducibility and extensibility. Comparative analysis shows that our system outperforms the legacy knowledge-based Jill Watson as well as the OpenAI Assistants service. We employ many safety measures that reduce instances of hallucinations and toxicity. The paper also includes real-world examples from a classroom setting that demonstrate different features of Jill Watson and its effectiveness.

Rochan H. Madhusudhana, Rahul K. Dass, Jeanette Luu et al.

In online learning, the ability to provide quick and accurate feedback to learners is crucial. In skill-based learning, learners need to understand the underlying concepts and mechanisms of a skill to be able to apply it effectively. While videos are a common tool in online learning, they cannot comprehend or assess the skills being taught. Additionally, while Generative AI methods are effective in searching and retrieving answers from a text corpus, it remains unclear whether these methods exhibit any true understanding. This limits their ability to provide explanations of skills or help with problem-solving. This paper proposes a novel approach that merges Cognitive AI and Generative AI to address these challenges. We employ a structured knowledge representation, the TMK (Task-Method-Knowledge) model, to encode skills taught in an online Knowledge-based AI course. Leveraging techniques such as Large Language Models, Chain-of-Thought, and Iterative Refinement, we outline a framework for generating reasoned explanations in response to learners' questions about skills.

Rhea Basappa, Mustafa Tekman, Hong Lu et al.

Social AI agents interact with members of a community, thereby changing the behavior of the community. For example, in online learning, an AI social assistant may connect learners and thereby enhance social interaction. These social AI assistants too need to explain themselves in order to enhance transparency and trust with the learners. We present a method of self-explanation that uses introspection over a self-model of an AI social assistant. The self-model is captured as a functional model that specifies how the methods of the agent use knowledge to achieve its tasks. The process of generating self-explanations uses Chain of Thought to reflect on the self-model and ChatGPT to provide explanations about its functioning. We evaluate the self-explanation of the AI social assistant for completeness and correctness. We also report on its deployment in a live class.

Karan Taneja, Ashok K. Goel

Multimodal AI is an important step towards building effective tools to leverage multiple modalities in human-AI communication. Building a multimodal document-grounded AI system to interact with long documents remains a challenge. Our work aims to fill the research gap of directly leveraging grounded visuals from documents alongside textual content in documents for response generation. We present an interactive conversational AI agent 'MuDoC' based on GPT-4o to generate document-grounded responses with interleaved text and figures. MuDoC's intelligent textbook interface promotes trustworthiness and enables verification of system responses by allowing instant navigation to source text and figures in the documents. We also discuss qualitative observations based on MuDoC responses highlighting its strengths and limitations.

Junsoo Park, Youssef Medhat, Htet Phyo Wai et al.

Learner representations play a central role in educational AI systems, yet it is often unclear whether they preserve meaningful differences between students when instructional outcomes are unavailable or highly context-dependent. This work examines how to evaluate learner representations based on whether they retain separation between learners under a shared comparison rule. We introduce distinctiveness, a representation-level measure that evaluates how each learner differs from others in the cohort using pairwise distances, without requiring clustering, labels, or task-specific evaluation. Using student-authored questions collected through a conversational AI agent in an online learning environment, we compare representations based on individual questions with representations that aggregate patterns across a student's interactions over time. Results show that learner-level representations yield higher separation, stronger clustering structure, and more reliable pairwise discrimination than interaction-level representations. These findings demonstrate that learner representations can be evaluated independently of instructional outcomes and provide a practical pre-deployment criterion using distinctiveness as a diagnostic metric for assessing whether a representation supports differentiated modeling or personalization.

Karan Taneja, Anjali Singh, Ashok K. Goel

Multimodal Large Language Models (MLLMs) offer an opportunity to support multimedia learning through conversational systems grounded in educational content. However, while conversational AI is known to boost engagement, its impact on learning in visually-rich STEM domains remains under-explored. Moreover, there is limited understanding of how multimodality and conversationality jointly influence learning in generative AI systems. This work reports findings from a randomized controlled online study (N = 124) comparing three approaches to learning biology from textbook content: (1) a document-grounded conversational AI with interleaved text-and-image responses (MuDoC), (2) a document-grounded conversational AI with text-only responses (TexDoC), and (3) a textbook interface with semantic search and highlighting (DocSearch). Learners using MuDoC achieved the highest post-test scores and reported the most positive learning experience. Notably, while TexDoC was rated as significantly more engaging and easier to use than DocSearch, it led to the lowest post-test scores, revealing a disconnect between student perceptions and learning outcomes. Interpreted through the lens of the Cognitive Load Theory, these findings suggest that conversationality reduces extraneous load, while visual-verbal integration induced by multimodality increases germane load, leading to better learning outcomes. When conversationality is not complemented by multimodality, reduced cognitive effort may instead inflate perceived understanding without improving learning outcomes.

Karan Taneja, Anjali Singh, Ashok K. Goel

Multimedia learning using text and images has been shown to improve learning outcomes compared to text-only instruction. But conversational AI systems in education predominantly rely on text-based interactions while multimodal conversations for multimedia learning remain unexplored. Moreover, deploying conversational AI in learning contexts requires grounding in reliable sources and verifiability to create trust. We present MuDoC, a Multimodal Document-grounded Conversational AI system based on GPT-4o, that leverages both text and visuals from documents to generate responses interleaved with text and images. Its interface allows verification of AI generated content through seamless navigation to the source. We compare MuDoC to a text-only system to explore differences in learner engagement, trust in AI system, and their performance on problem-solving tasks. Our findings indicate that both visuals and verifiability of content enhance learner engagement and foster trust; however, no significant impact in performance was observed. We draw upon theories from cognitive and learning sciences to interpret the findings and derive implications, and outline future directions for the development of multimodal conversational AI systems in education.

Rahul K. Dass, Rochan H. Madhusudhana, Erin C. Deye et al.

Supporting learners' understanding of taught skills in online settings is a longstanding challenge. While exercises and chat-based agents can evaluate understanding in limited contexts, this challenge is magnified when learners seek explanations that delve into procedural knowledge (how things are done) and reasoning (why things happen). We hypothesize that an intelligent agent's ability to understand and explain learners' questions about skills can be significantly enhanced using the TMK (Task-Method-Knowledge) model, a Knowledge-based AI framework. We introduce Ivy, an intelligent agent that leverages an LLM and iterative refinement techniques to generate explanations that embody teleological, causal, and compositional principles. Our initial evaluation demonstrates that this approach goes beyond the typical shallow responses produced by an agent with access to unstructured text, thereby substantially improving the depth and relevance of feedback. This can potentially ensure learners develop a comprehensive understanding of skills crucial for effective problem-solving in online environments.

William Broniec, Sungeun An, Spencer Rugaber et al.

COVID-19 continues to spread across the country and around the world. Current strategies for managing the spread of COVID-19 include social distancing. We present VERA, an interactive AI tool, that first enables users to specify conceptual models of the impact of social distancing on the spread of COVID-19. Then, VERA automatically spawns agent-based simulations from the conceptual models, and, given a data set, automatically fills in the values of the simulation parameters from the data. Next, the user can view the simulation results, and, if needed, revise the simulation parameters and run another experimental trial, or build an alternative conceptual model. We describe the use VERA to develop a SIR model for the spread of COVID-19 and its relationship with healthcare capacity.