arXiv:2604.14444v1 Announce Type: cross Abstract: Ensuring the reliability of machine learning-based intrusion detection systems remains a critical challenge in Internet of Things (IoT) environments, particularly as data poisoning attacks increasingly threaten the integrity of model training pipelines. This study evaluates the susceptibility of four widely used classifiers, Random Forest, Gradient Boosting Machine, Logistic Regression, and […]
DR$^3$-Eval: Towards Realistic and Reproducible Deep Research Evaluation
arXiv:2604.14683v1 Announce Type: new Abstract: Deep Research Agents (DRAs) aim to solve complex, long-horizon research tasks involving planning, retrieval, multimodal understanding, and report generation, yet their evaluation remains challenging due to dynamic web environments and ambiguous task definitions. We propose DR$^3$-Eval, a realistic and reproducible benchmark for evaluating deep research agents on multimodal, multi-file report […]
Attack Selection Reduces Safety in Concentrated AI Control Settings against Trusted Monitoring
arXiv:2602.04930v2 Announce Type: replace-cross Abstract: Future AI deployments will likely be monitored for malicious behaviour. The ability of these AIs to subvert monitors by adversarially selecting against them – attack selection – is particularly concerning. To study this, we let a red team create attack policies that attempt to insert attacks into code without being […]
CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations
arXiv:2604.14691v1 Announce Type: new Abstract: LLM-empowered agent simulations are increasingly used to study social emergence, yet the micro-to-macro causal mechanisms behind macro outcomes often remain unclear. This is challenging because emergence arises from intertwined agent interactions and meso-level feedback and nonlinearity, making generative mechanisms hard to disentangle. To this end, we introduce textbftextscCAMO, an automated […]
VisPCO: Visual Token Pruning Configuration Optimization via Budget-Aware Pareto-Frontier Learning for Vision-Language Models
arXiv:2604.15188v1 Announce Type: cross Abstract: Visual token pruning methods effectively mitigate the quadratic computational growth caused by processing high-resolution images and video frames in vision-language models (VLMs). However, existing approaches rely on predefined pruning configurations without determining whether they achieve computation-performance optimality. In this work, we introduce , a novel framework that formulates visual token […]
SynHAT: A Two-stage Coarse-to-Fine Diffusion Framework for Synthesizing Human Activity Traces
arXiv:2604.14705v1 Announce Type: new Abstract: Human activity traces (HATs) are critical for many applications, including human mobility modeling and point-of-interest (POI) recommendation. However, growing privacy concerns have severely limited access to authentic large-scale HAT datasets. Recent advances in generative AI provide new opportunities to synthesize realistic and privacy-preserving HATs for such applications. Yet two major […]
Efficient Search of Implantable Adaptive Cells for Medical Image Segmentation
arXiv:2604.14849v1 Announce Type: cross Abstract: Purpose: Adaptive skip modules can improve medical image segmentation, but searching for them is computationally costly. Implantable Adaptive Cells (IACs) are compact NAS modules inserted into U-Net skip connections, reducing the search space compared with full-network NAS. However, the original IAC framework still requires a 200-epoch differentiable search for each […]
SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval
arXiv:2604.14712v1 Announce Type: new Abstract: LLM-powered systems require complex multi-step decision-making abilities to solve real-world tasks, yet current planning approaches face a trade-off between the high latency of inference-time search and the limited generalization of supervised fine-tuning. To address this limitation, we introduce textbfSGA-MCTS, a framework that casts LLM planning as non-parametric retrieval. Offline, we […]
Agentic Explainability at Scale: Between Corporate Fears and XAI Needs
arXiv:2604.14984v1 Announce Type: cross Abstract: As companies enter the race for agentic AI adoption, fears surface around agentic autonomy and its subsequent risks. These fears compound as companies scale their agentic AI adoption with low-code applications, without a comparable scaling in their governance processes and expertise resulting in a phenomenon known as “Agent Sprawl”. While […]
The Agentification of Scientific Research: A Physicist’s Perspective
arXiv:2604.14718v1 Announce Type: new Abstract: This article argues that the most important significance of the AI revolution, especially the rise of large language models, lies not simply in automation, but in a fundamental change in how complex information and human know-how are carried, replicated, and shared. From this perspective, AI for Science is especially important […]
To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs
arXiv:2603.18373v2 Announce Type: replace-cross Abstract: When VLMs answer correctly, do they genuinely rely on visual information or exploit language shortcuts? We introduce the Tri-Layer Diagnostic Framework, which disentangles hallucination sources via three metrics: Latent Anomaly Detection (perceptual awareness), Visual Necessity Score (visual dependency, measured via KL divergence), and Competition Score (conflict between visual grounding and […]
Disentangle-then-Refine: LLM-Guided Decoupling and Structure-Aware Refinement for Graph Contrastive Learning
arXiv:2604.14746v1 Announce Type: new Abstract: Conventional Graph Contrastive Learning (GCL) on Text-Attributed Graphs (TAGs) relies on blind stochastic augmentations, inadvertently entangling task-relevant signals with noise. We propose SDM-SCR, a robust framework anchored in Approximate Orthogonal Decomposition. First, the Semantic Decoupling Module (SDM) leverages the instruction-following capability of Large Language Models (LLMs) to actively parse raw […]