Related papers: Intermediate Artifacts as First-Class Citizens: A …
Large-language-model (LLM)-based AI agents have recently showcased impressive versatility by employing dynamic reasoning, an adaptive, multi-step process that coordinates with external tools. This shift from static, single-turn inference to…
In this preprint, we present A collaborative human-AI approach to building an inspectable semantic layer for Agentic AI. AI agents first propose candidate knowledge structures from diverse data sources; domain experts then validate,…
Workflow support typically focuses on single simulation experiments. This is also the case for simulation based on finite element methods. If entire simulation studies shall be supported, flexible means for intertwining revising the model,…
Foundation models have reshaped AI by unifying fragmented architectures into scalable backbones with multimodal reasoning and contextual adaptation. In parallel, the long-standing notion of AI agents, defined by the sensing-decision-action…
In this paper, we offer a guide for researchers on evaluating reasoning in language models, building the case that reasoning should be assessed through evidence of adaptive, multi-step search rather than final-answer accuracy alone. Under…
Large language models (LLMs) are often portrayed as merely imitating linguistic patterns without genuine understanding. We argue that recent findings in mechanistic interpretability (MI), the emerging field probing the inner workings of…
This work examines how AI, especially agentic systems, is being adopted in engineering and manufacturing workflows, what value it provides today, and what is needed for broader deployment. This is an exploratory and qualitative…
General purpose intelligent learning agents cycle through (complex,non-MDP) sequences of observations, actions, and rewards. On the other hand, reinforcement learning is well-developed for small finite state Markov Decision Processes…
Along the design process of interactive system many intermediate artefacts (such as user interface prototypes, task models describing user work and activities, dialog models specifying system behavior, interaction models describing user…
From extracting features to generating text, the outputs of large language models (LLMs) typically rely on the final layers, following the conventional wisdom that earlier layers capture only low-level cues. However, our analysis shows that…
Large language models have advanced rapidly, from pattern recognition to emerging forms of reasoning, yet they remain confined to linguistic simulation rather than grounded understanding. They can produce fluent outputs that resemble…
Artificial Intelligence (AI) started out with an ambition to reproduce the human mind, but, as the sheer scale of that ambition became manifest, it quickly retreated into either studying specialized intelligent behaviours, or proposing…
AI alignment is about ensuring AI systems only pursue goals and activities that are beneficial to humans. Most of the current approach to AI alignment is to learn what humans value from their behavioural data. This paper proposes a…
This chapter argues that the reliability of agentic and generative AI is chiefly an architectural property. We define agentic systems as goal-directed, tool-using decision makers operating in closed loops, and show how reliability emerges…
AI systems are often used to make or contribute to important decisions in a growing range of applications, including criminal justice, hiring, and medicine. Since these decisions impact human lives, it is important that the AI systems act…
As intelligent systems are developed across diverse substrates - from machine learning models and neuromorphic hardware to in vitro neural cultures - understanding what gives a system agency has become increasingly important. Existing…
Presentations are a primary medium for scholarly communication, yet most AI slide generators optimize the artifact (a visually plausible deck) while under-optimizing the delivery process (pacing, narrative, and presentation preparation). We…
Agentic artificial intelligence systems are autonomous technologies capable of pursuing complex goals with minimal human oversight and are rapidly emerging as the next frontier in AI. While these systems promise major gains in productivity,…
Supplementary Training on Intermediate Labeled-data Tasks (STILTs) is a widely applied technique, which first fine-tunes the pretrained language models on an intermediate task before on the target task of interest. While STILTs is able to…
AI tools are being deployed over MBSE models today, and those models were not designed for this kind of consumption. The problem is not simply that tools hallucinate: well-prompted frontier models produce competent, useful output over a…