AI News

From Language Models to World-Acting Systems: Progress and Limits of Agentic AI across Digital, Social, Virtual, and Physical Environments (arxiv.org)

BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference (arxiv.org)

Reinforcement Learning for Sequential Solar PV Policy Design under Uncertainty: An Agent-Based Approach (arxiv.org)

DODR: Deterministic Operator-Driven Reasoning in Latent Space (arxiv.org)

Fast Gauss Sums via Flash Attention (arxiv.org)

On-board ML for Trace Gas detection in Imaging Spectroscopy data (arxiv.org)

MCPO: Modality-Contrastive Preference Optimization for Multimodal Chain-of-Thought Compression (arxiv.org)

ARIA - An Agentic Framework for Autonomous Testing of Infotainment Systems (arxiv.org)

TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networks (arxiv.org)

RefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Refactoring Agents (arxiv.org)

Attention-guided super-resolution of 4D flow MRI in carotid arteries (arxiv.org)

SimFuse3D: Source-Guided Target Simulation and Confidence-Guided Multi-Stage Localization Reweighting for Cross-Platform 3D Object Detection (arxiv.org)

ReCAST: Restoration-aware Cascaded Stage-wise Training for Obfuscated SMS Risk Classification (arxiv.org)

Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents (arxiv.org)

PRISM-Bench: An Audio-Centric Diagnostic Benchmark for Text-to-Audio-Video Generation (arxiv.org)

Mitigating Performance Discrepancy in Cross-Domain 3D Class-Incremental Learning (arxiv.org)

CC-Mediation: Evaluating Large Language Models for Cross-Cultural Conflict Mediation (arxiv.org)

MMTClinic: Multimodal, Multilingual Time Series Question Answering and Reasoning Benchmark for Clinical Domain (arxiv.org)

MABPD: Multi-Agent Bias Probing & Detection via Structured Argument Debate (arxiv.org)

Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair (arxiv.org)

Predicting Spatiotemporal Mobile Sensing-Based PM2.5 Concentrations Using Low-Rank Adapted Spatially Attentive Graph Neural Network (arxiv.org)

ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies (arxiv.org)

Distill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendation (arxiv.org)

Optimal Rates for Agentic Networked Information Aggregation (arxiv.org)

How Does mHC Use Its Residual Streams? Selective Routing and Near-Identity Mixing (arxiv.org)

GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detection (arxiv.org)

PRICE: A Systematic Study of LLM Adaptation Choices for Bitcoin Price Forecasting (arxiv.org)

Hessian-based molecular conformation augmentation for a scalable and efficient strategy of machine learning interatomic potentials (arxiv.org)

FedDRAW: Federated Dual Reputation Annealing Weighting for Heterogeneous Multi-Institutional Chest Radiograph Classification (arxiv.org)

Phase Transition Frequency as a Training Time Predictor of Test Accuracy in ResNets (arxiv.org)

Variational Continuation for Double Pendulum Periodic Orbits (arxiv.org)

Beyond Stationarity in Time Series: Discovering Causal Structures and Latent Regimes via Markov Blankets (arxiv.org)

From 80x to 385x: A Best-Matching-Unit Search at the L2 Roof, Measured Against a Symmetrically Tuned Baseline (arxiv.org)

MomentQuant: an even more minimalist interval method with linear time complexity for time series classification (arxiv.org)

Coarse-Graining Hidden Representations: Unsupervised Neuron Selection via Mapping Entropy (arxiv.org)

Dual-Scale State-Space Modeling with Speaker-Wise Dynamic CRF for Speech Emotion Recognition in Conversation (arxiv.org)

Relocation of compact sets in $\mathbb{R}^n$ by diffeomorphisms and linear separability of datasets in $\mathbb{R}^n$ (arxiv.org)

Brain4FMs: A Benchmark of Foundation Models for Electrical Brain Signal (arxiv.org)

Consensus Group Relative Policy Optimization for Text Generation (arxiv.org)

Train What You Deploy:Token-Faithful Post-Training of a Production Coding (arxiv.org)

Multi-Modal Time Series Prediction via Mixture of Modulated Experts (arxiv.org)

GLOW: Graph-Language Co-Encoding for Agentic Workflow Performance Prediction (arxiv.org)

Forecast Skill Is Not Decision Skill: Evidence from Weather-Dependent Decision Tasks (arxiv.org)

Fractal and Chaotic Activation Functions in Echo State Networks: Preprocessing Topology Governs the Echo State Property (arxiv.org)

How to Speculate about Uncertainty in Agentic Coding? A Draft-Model Gate Method (arxiv.org)

Partial Inverse Design of High-Performance Concrete Using Cooperative Neural Networks for Constraint-Aware Mix Generation (arxiv.org)

ResLearn-XR: Residual Learning for Network Traffic and Quality-of-Experience-Aware Modeling in Extended Reality (arxiv.org)

AlcaTRAz - Anchored Tree-Rule Defense Against Jailbreaks (arxiv.org)

A Deep Generative Model for Synthesizing Labeled Wireless Signals (arxiv.org)

Molecular D\'ej\`a Vu: Digit-Level Retrieval of Published Values in Frontier Language Models (arxiv.org)