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

Why I ditched the standard Python stack to run Qwen3-VL on an OrangePi 4 — and the hardware-specific “horror stories” that nearly broke me. Let’s be real: the AI world is currently high on “clever prompts.” Everyone is a “Prompt Engineer” until they have to build a safety system for a warehouse robot or a real-time monitor for a smart city. In the high-stakes world of Industry 4.0, a prompt is just a string. To actually do something, […]

Ver mais

arXiv:2602.16894v1 Announce Type: new Abstract: In response to the exponential growth in the use of artificial intelligence and machine learning applications, educators, researchers and policymakers have taken steps to integrate artificial intelligence applications into K-12 education. Among these efforts, one equally important approach has received little, if any attention: What if students and teachers were not just learning to be competent users of AI but also its creators? This question is at the heart of CreateAI in which […]

Ver mais

arXiv:2601.05395v1 Announce Type: new Abstract: Data-driven control offers a powerful alternative to traditional model-based methods, particularly when accurate system models are unavailable or prohibitively complex. While existing data-driven control methods primarily aim to construct controllers directly from measured data, our approach uses the available data to assess fundamental system-theoretic properties. This allows the informed selection of suitable control strategies without explicit model identification. We provide data-based conditions characterizing the (vector) relative degree and the stability of the zero […]

Ver mais

To address the challenges of synthetic aperture radar (SAR) ship detection in complex port environments, including strong background clutter, large-scale variations, and frequent missed detections of small vessels, this paper proposes a lightweight attention-guided multi-scale fusion detector, termed LAMFDet, based on YOLOv8. The proposed framework enhances the baseline architecture from three complementary perspectives: multi-scale feature enhancement, lightweight adaptive feature extraction, and efficient feature reconstruction. Specifically, a multi-scale feature enhancement module (SPPFSENetV2) integrating spatial pyramid pooling with channel attention […]

Ver mais

arXiv:2602.21389v1 Announce Type: new Abstract: Autonomous robots can transform how we observe marine ecosystems, but close-range operation in reefs and other cluttered habitats remains difficult. Vehicles must maneuver safely near animals and fragile structures while coping with currents, variable illumination and limited sensing. Previous approaches simplify these problems by leveraging soft materials and bioinspired swimming designs, but such platforms remain limited in terms of deployable autonomy. Here we present a sea turtle-inspired autonomous underwater robot that closed the […]

Ver mais

Personal AI agents incur substantial cost via repeated LLM calls. We show existing caching methods fail: GPTCache achieves 37.9% accuracy on real benchmarks; APC achieves 0-12%. The root cause is optimizing for the wrong property — cache effectiveness requires key consistency and precision, not classification accuracy. We observe cache-key evaluation reduces to clustering evaluation and apply V-measure decomposition to separate these on n=8,682 points across MASSIVE, BANKING77, CLINC150, and NyayaBench v2, our new 8,514-entry multilingual agentic dataset (528 […]

Ver mais