Related papers: TermAdventure: Interactively Teaching UNIX Command…
We consider the task of learning to play families of text-based computer adventure games, i.e., fully textual environments with a common theme (e.g. cooking) and goal (e.g. prepare a meal from a recipe) but with different specifics; new…
Performing diagnosis or exploratory analysis during the training of deep learning models is challenging but often necessary for making a sequence of decisions guided by the incremental observations. Currently available systems for this…
Executable scientific papers contain not just layouted text for reading. They contain, or link to, machine-comprehensible representations of the scientific findings or experiments they describe. Client-side players can thus enable readers…
Despite the rapid progress, LLMs for sequential decision-making (i.e., LLM agents) still struggle to produce diverse outputs. This leads to insufficient exploration, convergence to sub-optimal solutions, and becoming stuck in loops. Such…
The growing replication crisis across disciplines such as economics, finance, and other social sciences as well as computer science undermines the credibility of academic research. Current institutional solutions -- such as artifact…
Simulating learner actions helps stress-test open-ended interactive learning environments and prototype new adaptations before deployment. While recent studies show the promise of using large language models (LLMs) for simulating human…
Serious games are gaining popularity as effective teaching and learning tools, providing engaging, interactive, and practical experiences for students. Gamified learning experiences, such as virtual escape rooms, have emerged as powerful…
New types of Trusted Execution Environment (TEE) architectures like TrustLite and Intel Software Guard Extensions (SGX) are emerging. They bring new features that can lead to innovative security and privacy solutions. But each new TEE…
Dynamically typed programming languages are popular in education and the software industry. While presenting a low barrier to entry, they suffer from run-time type errors and longer-term problems in code quality and maintainability.…
As large language models increasingly mediate firm - customer interactions, firms face a tradeoff: the most capable models perform well but are costly and difficult to control at scale. Existing knowledge distillation methods address this…
Large language model (LLM)-based computer use agents execute user commands by interacting with available UI elements, but little is known about how users want to interact with these agents or what design factors matter for their user…
Text based games are simulations in which an agent interacts with the world purely through natural language. They typically consist of a number of puzzles interspersed with interactions with common everyday objects and locations. Deep…
To cooperate with humans effectively, virtual agents need to be able to understand and execute language instructions. A typical setup to achieve this is with a scripted teacher which guides a virtual agent using language instructions.…
Traditional cybersecurity tabletop exercises (TTXs) provide valuable training but are often scripted, resource-intensive, and difficult to scale. We introduce AgentBnB, a browser-based re-imagining of the Backdoors & Breaches game that…
Developing excavation autonomy is challenging given the environments where excavators operate, the complexity of physical interaction and the degrees of freedom of operation of the excavator itself. Simulation is a useful tool to build…
Analyzing texts such as open-ended responses, headlines, or social media posts is a time- and labor-intensive process highly susceptible to bias. LLMs are promising tools for text analysis, using either a predefined (top-down) or a…
Explainable Artificial Intelligence (XAI) plays a critical role in fostering user trust and understanding in AI-driven systems. However, the design of effective XAI interfaces presents significant challenges, particularly for UX…
This paper presents an approach to learning from situated, interactive tutorial instruction within an ongoing agent. Tutorial instruction is a flexible (and thus powerful) paradigm for teaching tasks because it allows an instructor to…
"Computational experiments" use code and interactive visualizations to convey mathematical and physical concepts in an intuitive way, and are increasingly used to support ex cathedra lecturing in scientific and engineering disciplines.…
Unsupervised environment design (UED) is a form of automatic curriculum learning for training robust decision-making agents to zero-shot transfer into unseen environments. Such autocurricula have received much interest from the RL…