April 2026

arXiv:2604.18612v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated strong capabilities in complex reasoning tasks, while recent prompting strategies such as Chain-of-Thought (CoT) have further elevated their performance in handling complex logical problems. Despite these advances, high-quality reasoning remains heavily reliant on manual static prompts and is sensitive to decoding configurations and task distributions, leading to performance fluctuations and limited transferability. Existing automatic prompt optimization methods typically adopt single-agent local search, failing to simultaneously optimize prompts […]

Ver mais

arXiv:2604.18611v1 Announce Type: new Abstract: Anomaly detection in nuclear industrial control systems (ICS) requires continuous, energy-efficient monitoring across multiple subsystems that are often deployed at different stages of plant commissioning. When a conventional neural network is sequentially trained to monitor new subsystems, it catastrophically forgets previously learned anomaly patterns, a safety-critical failure mode. We present the first spiking neural network (SNN)-based anomaly detection system with continual learning for nuclear ICS, addressing both challenges simultaneously. Our approach introduces spike-encoded […]

Ver mais

arXiv:2604.18610v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress but incur substantial computational overhead and energy consumption during inference, limiting deployment in resource-constrained environments. Spiking Neural Networks (SNNs), with their sparse event-driven computation, offer inherent energy efficiency advantages on neuromorphic hardware, yet extending them to MLLMs faces two key challenges: heterogeneous modalities make uniform spike encoding insufficient, and high-resolution image inputs amplify timestep unfolding overhead. We propose SpikeMLLM, the first spike-based framework for […]

Ver mais

arXiv:2604.18607v1 Announce Type: new Abstract: LLM-driven program evolution can discover high-quality programs, but its cost and run-to-run variance hinder reliable progress. We propose TurboEvolve, a multi-island evolutionary framework that improves sample efficiency and robustness under fixed evaluation budgets. Inspired by the multiple-offspring strategy in evolutionary algorithms, TurboEvolve introduces verbalized Sampling, prompting the LLM to emit K diverse candidates with explicit self-assigned sampling weights, and an online scheduler that adapts K to expand exploration under stagnation and reduce overhead […]

Ver mais

arXiv:2604.18595v1 Announce Type: new Abstract: To support mission-critical services in emergency scenarios, wireless networks are required to provide stringent guarantees under massive Ultra-Reliable Low-Latency Communications (mURLLC) constraints. Distributed unmanned aerial vehicle (UAV)-based massive multiple-input multiple-output (MIMO) architectures have recently emerged as a promising solution for rapidly deployable emergency communication systems. However, how to fundamentally characterize and guarantee statistical quality-of-service (QoS) for such systems in the finite blocklength regime remains largely unexplored. To overcome these challenges, in this paper […]

Ver mais

arXiv:2604.18593v1 Announce Type: new Abstract: This paper presents the design of HELIX, an end-to-end verified code generation system with a focus on the intersection of high-performance and high-assurance numerical computing. The code generation can be fine-tuned to generate efficient code for a broad set of computer architectures while providing formal guarantees of the correctness of such generated code. Using a real-life example of a cyber-physical robot system, this paper demonstrates how, by using HELIX, one can start from […]

Ver mais

arXiv:2604.18592v1 Announce Type: new Abstract: We introduce a two-dimensional (2D) early exit strategy that coordinates layer-wise and sentence-wise exiting for classification tasks in large language models. By processing input incrementally sentence-by-sentence while progressively activating deeper layers, our method achieves multiplicative computational savings that exceed those from optimizing either dimension independently. Experimental evaluation across four state-of-the-art LLMs (Llama 3.1, Llama 3.2, Gemma, Qwen; 3B-8B parameters) on three sentiment classification datasets demonstrates additional speed-ups of 1.4–2.3$times$ over optimal layer-wise early […]

Ver mais

arXiv:2604.18591v1 Announce Type: new Abstract: Game UI implementation requires translating stylized mockups into interactive engine entities. However, current “Screenshot-to-Code” tools often struggle with the irregular geometries and deep visual hierarchies typical of game interfaces. To bridge this gap, we introduce SPRITE, a pipeline that transforms static screenshots into editable engine assets. By integrating Vision-Language Models (VLMs) with a structured YAML intermediate representation, SPRITE explicitly captures complex container relationships and non-rectangular layouts. We evaluated SPRITE against a curated Game […]

Ver mais

arXiv:2604.18590v1 Announce Type: new Abstract: The growing use of artificial intelligence (AI) in education, professional work, and everyday problem-solving has raised important questions about its effect on human reasoning. While AI can improve efficiency, save time, and support learning, repeated dependence on it may also encourage cognitive offloading, reduce productive struggle, and weaken independent critical thinking. This paper investigates the relationship between AI-use behavior and critical-thinking performance through an interview-based survey combined with short logic and reasoning tasks. […]

Ver mais

arXiv:2604.18589v1 Announce Type: new Abstract: Thematic analysis is difficult to scale: manual workflows are labor-intensive, while fully automated pipelines often lack controllability and transparent evaluation. We present textbf{CentaurTA Studio}, a web-based system for self-improving human–agent collaboration in open coding and theme construction. The system integrates (1) a two-stage human feedback pipeline separating simulator drafting and expert validation, (2) persistent prompt optimization that distills validated feedback into reusable alignment principles, and (3) rubric-based evaluation with early stopping for process […]

Ver mais