arXiv:2406.03707v2 Announce Type: replace-cross Abstract: Autoregressive language models have demonstrated a remarkable ability to extract latent structure from text. The embeddings from large language models have been shown to capture aspects of the syntax and semantics of language. But what should embeddings represent? We connect the autoregressive prediction objective to the idea of constructing predictive sufficient statistics to summarize the information contained in a sequence of observations, and use this connection to identify three settings where the optimal […]

Ver mais

arXiv:2601.06462v1 Announce Type: new Abstract: Applying Physics-Informed Gaussian Process Regression to the eigenvalue problem $(mathcal{L}-lambda)u = 0$ poses a fundamental challenge, where the null source term results in a trivial predictive mean and a degenerate marginal likelihood. Drawing inspiration from system identification, we construct a transfer function-type indicator for the unknown eigenvalue/eigenfunction using the physics-informed Gaussian Process posterior. We demonstrate that the posterior covariance is only non-trivial when $lambda$ corresponds to an eigenvalue of the partial differential operator […]

Ver mais

arXiv:2602.09163v1 Announce Type: new Abstract: Scientific knowledge bases accelerate discovery by curating findings from primary literature into structured, queryable formats for both human researchers and emerging AI systems. Maintaining these resources requires expert curators to search relevant papers, reconcile evidence across documents, and produce ontology-grounded annotations – a workflow that existing benchmarks, focused on isolated subtasks like named entity recognition or relation extraction, do not capture. We present FlyBench to evaluate AI agents on end-to-end agentic ontology curation […]

Ver mais

arXiv:2508.20257v2 Announce Type: replace-cross Abstract: The process of discovering equations from data lies at the heart of physics and in many other areas of research, including mathematical ecology and epidemiology. Recently, machine learning methods known as symbolic regression emerged as a way to automate this task. This study presents an overview of the current literature on symbolic regression, while also comparing the efficiency of five state-of-the-art methods in recovering the governing equations from nine processes, including chaotic dynamics […]

Ver mais

The scaling of large-scale AI systems increasingly encounters operational instabilities that cannot be attributed to interconnect limitations alone. Even in infrastructures with sufficient network capacity, cost escalation, non-deterministic behavior, and soft degradation persist, indicating coordination and control as distinct failure domains. Building on prior structural analyses of interconnect-induced instability, this article introduces runtime control coherence as a structural property describing the degree to which distributed control decisions across schedulers, orchestrators, runtime engines, and policy layers remain mutually consistent. […]

Ver mais

Introduction When writers think about LaTeX, they think about academic papers. Dense research documents filled with equations, citations, and footnotes. They don’t think about fantasy novels, thriller manuscripts, or literary fiction. That’s a missed opportunity. LaTeX—the typesetting system beloved by mathematicians and scientists—offers creative writers something word processors can’t match: programmable consistency. The same features that let physicists define custom notation for quantum equations let novelists define custom styling for character dialogue, narrative voices, and recurring textual elements. […]

Ver mais

arXiv:2601.00268v1 Announce Type: new Abstract: We introduce WildAGTEval, a benchmark designed to evaluate large language model (LLM) agents’ function-calling capabilities under realistic API complexity. Unlike prior work that assumes an idealized API system and disregards real-world factors such as noisy API outputs, WildAGTEval accounts for two dimensions of real-world complexity: 1. API specification, which includes detailed documentation and usage constraints, and 2. API execution, which captures runtime challenges. Consequently, WildAGTEval offers (i) an API system encompassing 60 distinct […]

Ver mais

arXiv:2602.04989v1 Announce Type: new Abstract: Online matching has been a mainstay in domains such as Internet advertising and organ allocation, but practical algorithms often lack strong theoretical guarantees. We take an important step toward addressing this by developing new online matching algorithms based on a coarsening approach. Although coarsening typically implies a loss of granularity, we show that, to the contrary, aggregating offline nodes into capacitated clusters can yield near-optimal theoretical guarantees. We apply our methodology to heart […]

Ver mais

arXiv:2601.19934v1 Announce Type: new Abstract: Large language models (LLMs) are widely used for tasks ranging from summarisation to decision support. In practice, identical prompts do not always produce identical outputs, even when temperature and other decoding parameters are fixed. In this work, we conduct repeated-run experiments to empirically quantify baseline behavioural drift, defined as output variability observed when the same prompt is issued multiple times under operator-free conditions. We evaluate two publicly accessible models, gpt-4o-mini and llama3.1-8b, across […]

Ver mais

arXiv:2601.15292v1 Announce Type: new Abstract: Diabetes is a significant and continuously rising health challenge in Indonesia. Although many artificial intelligence (AI)-based health applications have been developed for early detection, most function as “black boxes,” lacking transparency in their predictions. Explainable AI (XAI) methods offer a solution, yet their technical outputs are often incomprehensible to non-expert users. This research aims to develop a mobile application front-end that presents XAI-driven diabetes risk analysis in an intuitive, understandable format. Development followed […]

Ver mais