Related papers: Towards the AI Historian: Agentic Information Extr…

For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing the human level, with AI agents considered a promising vehicle for this pursuit. AI agents are artificial entities that sense their environment,…

Large language models (LLMs) are transforming scientific workflows, not only through their generative capabilities but also through their emerging ability to use tools, reason about data, and coordinate complex analytical tasks. Yet in most…

Building socially-intelligent AI agents (Social-AI) is a multidisciplinary, multimodal research goal that involves creating agents that can sense, perceive, reason about, learn from, and respond to affect, behavior, and cognition of other…

Artificial intelligence (AI) is transforming the practice of science. Machine learning and large language models (LLMs) can generate hypotheses at a scale and speed far exceeding traditional methods, offering the potential to accelerate…

Building and deploying machine learning solutions in healthcare remains expensive and labor-intensive due to fragmented preprocessing workflows, model compatibility issues, and stringent data privacy constraints. In this work, we introduce…

This essay aims to bid analogue historians assume that digitisation is the first step to creating historical heritage based on the new language of Science: Computer Science. As we know, Humanities disciplines cannot easily be encapsulated…

Scientific applications continue to rely on legacy Fortran codebases originally developed for homogeneous, CPU-based systems. As High-Performance Computing (HPC) shifts toward heterogeneous GPU-accelerated architectures, many accelerators…

Large Language Model (LLM) agents, acting on their users' behalf to manipulate and analyze data, are likely to become the dominant workload for data systems in the future. When working with data, agents employ a high-throughput process of…

Recent advances in Large Language Model (LLM) agents have enabled complex agentic workflows where models autonomously retrieve information, call tools, and reason over large corpora to complete tasks on behalf of users. Despite the growing…

Language models (LMs) are sentence-completion engines trained on massive corpora. LMs have emerged as a significant breakthrough in natural-language processing, providing capabilities that go far beyond sentence completion including…

Traditionally, neighborhood studies have used interviews, surveys, and manual image annotation guided by detailed protocols to identify environmental characteristics, including physical disorder, decay, street safety, and sociocultural…

We introduce Chronos, a simple yet effective framework for pretrained probabilistic time series models. Chronos tokenizes time series values using scaling and quantization into a fixed vocabulary and trains existing transformer-based…

This contribution is concerned with the following issue: can pretrained large language models (LLMs) be refined and customized to the point where they become virtual assistants helping experts with the effective use of a simulation tool? In…

Agentic AI require persistent memory to store user-specific histories beyond the limited context window of LLMs. Existing memory systems use dense vector databases or knowledge-graph traversal (or hybrid), incurring high retrieval latency…

A significant body of research in Artificial Intelligence (AI) has focused on generating stories automatically, either based on prior story plots or input images. However, literature has little to say about how users would receive and use…

While frontier large language models (LLMs) are capable tool-using agents, current AI systems still operate in a strict turn-based fashion, oblivious to passage of time. This synchronous design forces user queries and tool-use to occur…

Vision-Language Models (VLMs) transfer visual and textual data into a shared embedding space. In so doing, they enable a wide range of multimodal tasks, while also raising critical questions about the nature of machine 'understanding.' In…

Building autonomous agents able to grow open-ended repertoires of skills across their lives is a fundamental goal of artificial intelligence (AI). A promising developmental approach recommends the design of intrinsically motivated agents…

The rapid emergence of open-source, locally hosted intelligent agents marks a critical inflection point in human-computer interaction. Systems such as OpenClaw demonstrate that Large Language Model (LLM)-based agents can autonomously…

Historians, and in particular researchers in prosopography, focus a lot of effort on extracting and coding information from historical sources to build databases. To deal with this situation, they rely in some cases on their intuition. One…