AI News

EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents (arxiv.org)

RATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics (arxiv.org)

Competence-Aware Orchestration for LLM-Based Multi-Agent Systems (arxiv.org)

Retrieval-Augmented Multimodal Language Model with Heterogeneous Evidence Integration for Clinical Prognosis (arxiv.org)

Optimal Algorithms for Nonsmooth Nonconvex Stochastic Optimization with Constraints (arxiv.org)

DP-MIND: Differentially private memory-guided Long context Inference (arxiv.org)

A small cognitive core explains human behavior at scale (arxiv.org)

Tabular Foundation Models Are Effectively Shallow (arxiv.org)

State-OPD: State-Grounded On-Policy Distillation for Multi-Turn Agents (arxiv.org)

DAG Structure Learning with Node-Varying Heavy-Tailed Disturbances (arxiv.org)

Provenance-Aware Belief Updating in Human-AI Feedback Loops (arxiv.org)

Scaling Empowered Agents (arxiv.org)

EliteTable: Self-Improving Program Search for Executable Control Policies (arxiv.org)

Beyond Discrepancy: Oracle Drift in Nonstationary Weighted Risk Minimization (arxiv.org)

Probabilistic Forecasting of Electric Vehicle Charging in a Time-varying Hierarchical Infrastructure (arxiv.org)

Gaussian BROJA Partial Information Decomposition in Closed Form (arxiv.org)

How Well Do Prior-Data Fitted Networks Amortize Bayesian Inference? (arxiv.org)

X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems (arxiv.org)

Studying Comics at Scale with Artificial Intelligence: The PAGE Framework and Three Studies of American Comics and Japanese Manga (arxiv.org)

Primal-Dual Flow Matching for Sample-Wise Constrained Generation (arxiv.org)

Learning Schwarzschild Geodesic Motion with Lagrangian Neural Networks (arxiv.org)

BLEND: Balancing Personalization vs. Generalization in Federated Vision-Language Models (arxiv.org)

Enriched Holomorphic Neural Networks for 2D and 3D Laplace Problems (arxiv.org)

Gaussian-Width Bounds for Offline-to-Online Linear Bandits (arxiv.org)

Diffusion Precipitation Generation with Medium-range Weather Forecasting (arxiv.org)

Double-Take: Improving Capacity, Binding, and Selectivity In Long-Context Within Bidirectional Memory (arxiv.org)

Humanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent Limits (arxiv.org)

Branching On-Policy Distillation (arxiv.org)

A Local Agentic AI Framework to Generate Edge Case Scenarios for Safety Assurance (arxiv.org)

SynAct: Synergistic Active Feedback Learning for LLM Agents (arxiv.org)

DataCupid: Stable Matching Repair for Training Data Acquisition with Delayed Feedback (arxiv.org)

Controlled-Minimax: Stabilizing Adversarial Optimization via Control Theory (arxiv.org)

SqueezeBench: Saturation-Resilient Evaluation of Mathematical Capability (arxiv.org)

Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models (arxiv.org)

Looking Ahead and Back: Anticipatory Generative Modeling for Road-Network Trajectories (arxiv.org)

How Much Computation Does Every Forecast Need? Structured Block Skipping in Two Time-Series Foundation Models (arxiv.org)

A Theory of the Mechanics of Information: Generalization Through Measurement of Uncertainty (Learning is Measuring) (arxiv.org)

Optimizable Model Averaging for Ensembling Heterogeneous Model Outputs (arxiv.org)

ReSFlow: Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation (arxiv.org)

CircuitTree: Composing Circuits into A Syllable Transcriber (arxiv.org)

An Input-Dependent Readout Phase for Resonant Sequence Models (arxiv.org)

Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QA (arxiv.org)

Tensor-based Fusion of Multi-modal Data for Predicting Cancer Risk Levels (arxiv.org)

Does Location Matter? A Black-Box Causal Audit Reveals Model-Dependent Audio Grounding in LALM Hallucination (arxiv.org)

REDaCT: Collapse-Free Unlearning in Large Reasoning Models (arxiv.org)

Meta-Reflective Evolution Effectively Improves Production AI Systems (arxiv.org)

An all-transistor physical-learning transformer can be trained to perform in-context learning (arxiv.org)

Locally Private Parametric Methods for Change-Point Detection (arxiv.org)

One-Step Text Generation by Seq-Drifting (arxiv.org)

Collaborative Theory of Mind: Learning to Self-Revise by Anticipating User Responses (arxiv.org)