arXiv:2604.05157v1 Announce Type: new Abstract: Computer-Use Agents (CUAs) leverage large language models to execute GUI operations on desktop environments, yet they generate actions without evaluating action quality, leading to irreversible errors that cascade through subsequent steps. We propose IntentScore, a plan-aware reward model that learns to score candidate actions from 398K offline GUI interaction steps […]
Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling
arXiv:2604.04987v1 Announce Type: cross Abstract: Speculative sampling (SpS) has been successful in accelerating the decoding throughput of auto-regressive large language models by leveraging smaller draft models. SpS strictly enforces the generated distribution to match that of the verifier LLM. This is unnecessarily restrictive as slight variations of the verifier’s distribution, such as sampling with top-$k$ […]
Stories of Your Life as Others: A Round-Trip Evaluation of LLM-Generated Life Stories Conditioned on Rich Psychometric Profiles
arXiv:2604.06071v1 Announce Type: cross Abstract: Personality traits are richly encoded in natural language, and large language models (LLMs) trained on human text can simulate personality when conditioned on persona descriptions. However, existing evaluations rely predominantly on questionnaire self-report by the conditioned model, are limited in architectural diversity, and rarely use real human psychometric data. Without […]
Evaluation of Embedding-Based and Generative Methods for LLM-Driven Document Classification: Opportunities and Challenges
arXiv:2604.04997v1 Announce Type: cross Abstract: This work presents a comparative analysis of embedding-based and generative models for classifying geoscience technical documents. Using a multi-disciplinary benchmark dataset, we evaluated the trade-offs between model accuracy, stability, and computational cost. We find that generative Vision-Language Models (VLMs) like Qwen2.5-VL, enhanced with Chain-of-Thought (CoT) prompting, achieve superior zero-shot accuracy […]
Bypassing the CSI Bottleneck: MARL-Driven Spatial Control for Reflector Arrays
arXiv:2604.05162v1 Announce Type: new Abstract: Reconfigurable Intelligent Surfaces (RIS) are pivotal for next-generation smart radio environments, yet their practical deployment is severely bottlenecked by the intractable computational overhead of Channel State Information (CSI) estimation. To bypass this fundamental physical-layer barrier, we propose an AI-native, data-driven paradigm that replaces complex channel modeling with spatial intelligence. This […]
Causal Stance
arXiv:2604.05004v1 Announce Type: cross Abstract: What exactly is the meaning of physical causal closure, a concept frequently discussed in the philosophy of mind? Jaegwon Kim explicitly adopts a conception of causation according to which physical causation is effectively identified with deterministic physical lawfulness, and on this basis equates physical determinism with physical causal closure. While […]
Solving a Stackelberg Game on Transportation Networks in a Dynamic Crime Scenario: A Mixed Approach on Multi-Layer Networks
arXiv:2406.14514v4 Announce Type: replace Abstract: Interdicting a criminal with limited police resources is a challenging task as the criminal changes location over time. The size of the large transportation network further adds to the difficulty of this scenario. To tackle this issue, we consider the concept of a layered graph. At each time stamp, we […]
Comparative Characterization of KV Cache Management Strategies for LLM Inference
arXiv:2604.05012v1 Announce Type: cross Abstract: Efficient inference with Large Language Models (LLMs) increasingly relies on Key-Value (KV) caches to store previously computed key and value vectors at each layer. These caches are essential to minimize redundant computation during autoregressive token generation, lowering computational complexity from quadratic to linear. However, the growth of KV caches has […]
Learning to Focus: CSI-Free Hierarchical MARL for Reconfigurable Reflectors
arXiv:2604.05165v1 Announce Type: new Abstract: Reconfigurable Intelligent Surfaces (RIS) has a potential to engineer smart radio environments for next-generation millimeter-wave (mmWave) networks. However, the prohibitive computational overhead of Channel State Information (CSI) estimation and the dimensionality explosion inherent in centralized optimization severely hinder practical large-scale deployments. To overcome these bottlenecks, we introduce a “CSI-free” paradigm […]
ID-Sim: An Identity-Focused Similarity Metric
arXiv:2604.05039v1 Announce Type: cross Abstract: Humans have remarkable selective sensitivity to identities — easily distinguishing between highly similar identities, even across significantly different contexts such as diverse viewpoints or lighting. Vision models have struggled to match this capability, and progress toward identity-focused tasks such as personalized image generation is slowed by a lack of identity-focused […]
Toward Virtuous Reinforcement Learning: A Critique and Roadmap
arXiv:2512.04246v2 Announce Type: replace Abstract: This paper critiques common patterns in machine ethics for Reinforcement Learning (RL) and argues for a virtue focused alternative. We highlight two recurring limitations in much of the current literature: (i) rule based (deontological) methods that encode duties as constraints or shields often struggle under ambiguity and nonstationarity and do […]
Dynamic Linear Coregionalization for Realistic Synthetic Multivariate Time Series
arXiv:2604.05064v1 Announce Type: cross Abstract: Synthetic data is essential for training foundation models for time series (FMTS), but most generators assume static correlations, and are typically missing realistic inter-channel dependencies. We introduce DynLMC, a Dynamic Linear Model of Coregionalization, that incorporates time-varying, regime-switching correlations and cross-channel lag structures. Our approach produces synthetic multivariate time series […]