arXiv:2602.15090v1 Announce Type: new Abstract: Agentic AI prototypes are being deployed across domains with increasing speed, yet no methodology for their structured design, governance, and prospective evaluation has been established. Existing AI documentation practices and guidelines – Model Cards, Datasheets, or NIST AI RMF – are either retrospective or lack machine-readability and interoperability. We present the Agentic Automation Canvas (AAC), a structured framework for the prospective design of agentic systems and a tool to facilitate communication between their […]

Ver mais

arXiv:2601.14268v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in medicine and clinical workflows, yet we know little about their decision and affective profiles. Taking a historically informed outlook on the future, we treated successive OpenAI models as an evolving lineage and compared them with humans in a gambling task with repeated happiness ratings. Computational analyses showed that some aspects became more human-like: newer models took more risks and displayed more human-like patterns of Pavlovian […]

Ver mais

arXiv:2602.18520v1 Announce Type: new Abstract: Providing timely, rubric-aligned feedback on student-drawn diagrams is a persistent challenge in STEM education. While large multimodal models (LMMs) can jointly parse images and generate explanations, their tendency to hallucinate undermines trust in classroom deployments. We present Sketch2Feedback, a grammar-in-the-loop framework that decomposes the problem into four stages — hybrid perception, symbolic graph construction, constraint checking, and constrained VLM feedback — so that the language model verbalizes only violations verified by an upstream […]

Ver mais

arXiv:2602.07059v1 Announce Type: new Abstract: Reproducibility is an important requirement in evolutionary computation, where results largely depend on computational experiments. In practice, reproducibility relies on how algorithms, experimental protocols, and artifacts are documented and shared. Despite growing awareness, there is still limited empirical evidence on the actual reproducibility levels of published work in the field. In this paper, we study the reproducibility practices in papers published in the Evolutionary Combinatorial Optimization and Metaheuristics track of the Genetic and […]

Ver mais

Accurate prediction of phase equilibria remains a central challenge in chemical engineering. Physics-consistent machine learning methods that incorporate thermodynamic structure into neural networks have recently shown strong performance for activity-coefficient modeling. However, extending such approaches to equilibrium data arising from an extremum principle, such as liquid-liquid equilibria, remains difficult. Here we present DISCOMAX, a differentiable algorithm for phase-equilibrium calculation that guarantees thermodynamic consistency at both training and inference, only subject to a user-specified discretization. The method is rooted […]

Ver mais

arXiv:2603.23640v1 Announce Type: new Abstract: Deploying large language models on-device for always-on personal agents demands sustained inference from hardware tightly constrained in power, thermal envelope, and memory. We benchmark Qwen 2.5 1.5B (4-bit quantised) across four platforms: a Raspberry Pi 5 with Hailo-10H NPU, a Samsung Galaxy S24 Ultra, an iPhone 16 Pro, and a laptop NVIDIA RTX 4050 GPU. Using a fixed 258-token prompt over 20 warm-condition iterations per device, we measure throughput, latency, power, and thermal […]

Ver mais

Recent progress in reinforcement learning with verifiable rewards (RLVR) shows that small, specialized language models (SLMs) can exhibit structured reasoning without relying on large monolithic LLMs. We introduce soft hidden-state collaboration, where multiple heterogeneous frozen SLM experts are integrated through their internal representations via a trainable attention interface. Experiments on Reasoning Gym and GSM8K show that this latent integration is competitive with strong single-model RLVR baselines. Ablations further reveal a dual mechanism of expert utilization: for simpler arithmetic […]

Ver mais

The Problem When building frontends, I didn’t want to hardcode JSON data everywhere. I wanted to build against actual API endpoints and practice the integration work, but spinning up a real backend for every prototype felt like overkill. After doing this dance too many times – writing throwaway Express servers or mocking fetch calls with static JSON – I realized other developers probably face this same friction. The typical workflow looked like this: 1. Start building a React […]

Ver mais

arXiv:2601.15470v1 Announce Type: new Abstract: In this paper, we consider outlier embeddings into HSTs and ultrametrics. In particular, for $(X,d)$, let $k$ be the size of the smallest subset of $X$ such that all but that subset (i.e. the “outlier set”) can be probabilistically embedded into the space of HSTs with expected distortion at most $c$. Our primary result is showing that there exists an efficient algorithm that takes in $(X,d)$ and a target distortion $c$ and samples […]

Ver mais