arXiv:2508.15008v3 Announce Type: replace-cross Abstract: The deployment of Quantized Neural Networks (QNNs) on resource-constrained devices, such as microcontrollers, has introduced significant challenges in balancing model performance, computational complexity, and memory constraints. Tiny Machine Learning (TinyML) addresses these issues by integrating…
arXiv:2509.07894v3 Announce Type: replace Abstract: Recently, the physical capabilities of (M)LLMs have garnered increasing attention. However, existing benchmarks for physics suffer from two major gaps: they neither provide systematic and up-to-date coverage of real-world physics competitions such as physics Olympiads,…
arXiv:2503.04782v2 Announce Type: replace-cross Abstract: Satisfiability Modulo Linear Integer Arithmetic, SMT(LIA) for short, is pivotal across various critical domains. Previous research has primarily focused on SMT solving techniques. However, in practical applications such as software and hardware testing, there is…
arXiv:2509.10837v1 Announce Type: new Abstract: Complex Query Answering (CQA) over incomplete Knowledge Graphs (KGs), typically formalized as reasoning with Existential First-Order predicate logic with one free variable (EFO$_1$), faces a fundamental trade-off between logical soundness and computational efficiency. This work…
arXiv:2509.10875v1 Announce Type: new Abstract: The concept of the ‘agent’ has profoundly shaped Artificial Intelligence (AI) research, guiding development from foundational theories to contemporary applications like Large Language Model (LLM)-based systems. This paper critically re-evaluates the necessity and optimality of…
arXiv:2509.10769v1 Announce Type: new Abstract: While individual components of agentic architectures have been studied in isolation, there remains limited empirical understanding of how different design dimensions interact within complex multi-agent systems. This study aims to address these gaps by providing…
arXiv:2509.10818v1 Announce Type: new Abstract: Difficult decision-making problems abound in various disciplines and domains. The proliferation of generative techniques, especially large language models (LLMs), has excited interest in using them for decision support. However, LLMs cannot yet resolve missingness in…
arXiv:2509.10762v1 Announce Type: new Abstract: AI answer engines increasingly mediate access to domain knowledge by generating responses and citing web sources. We introduce GEO-16, a 16 pillar auditing framework that converts on page quality signals into banded pillar scores and…
arXiv:2509.10707v1 Announce Type: new Abstract: As AI systems increasingly evaluate other AI outputs, understanding their assessment behavior becomes crucial for preventing cascading biases. This study analyzes vision-language descriptions generated by NVIDIA’s Describe Anything Model and evaluated by three GPT variants…
arXiv:2509.10704v1 Announce Type: new Abstract: Text-to-image (T2I) models, while offering immense creative potential, are highly reliant on human intervention, posing significant usability challenges that often necessitate manual, iterative prompt engineering over often underspecified prompts. This paper introduces Maestro, a novel…
