AI News

SMH-Bench: Benchmarking LLM Agents for Environment-Grounded Reasoning and Action in Smart Homes (arxiv.org)

Bayesian Spectral Emotion Transition Discovery from Multi-Annotator Disagreement (arxiv.org)

Escaping the Mode Lottery: Multi-Response Training Improves Language Model Generalization (arxiv.org)

Physically-Constrained Mamba-SDE for Remaining Useful Life Prediction under Irregular Observations (arxiv.org)

Absorbing Complexity: An Interaction-Native Knowledge Harness for Financial LLM Agents (arxiv.org)

EVA-Net: Subject-Independent EEG Motor Decoding with Video-Derived Motor Priors (arxiv.org)

WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis (arxiv.org)

Dive into Waves: Morlet Spectral Transformer for Cross-Subject Emotion Decoding from EEG (arxiv.org)

Task diversity produces systematic transfer but inhibits continual reinforcement learning (arxiv.org)

Enhancing LLM Metacognition via Cognitive Pairwise Training (arxiv.org)

CUPID in the Model Zoo: Online Matchmaking for Selecting Your Dream LLM (arxiv.org)

Online Packet Scheduling with Deadlines and Learning (arxiv.org)

Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction (arxiv.org)

Evaluation of Baseline Methods for IDD-based SSD External Memory Search (arxiv.org)

CAPF: Guiding Search-Agent Rollouts with Credit-Attenuated Privileged Feedback (arxiv.org)

An NLP-Driven Framework for Curriculum-Labor Market Alignment: Schema-Constrained LLM Extraction, ESCO-Anchored Semantic Matching, and Multi-Dimensional Gap Quantification (arxiv.org)

Token Predictors Are Not Planners: Building Physically Grounded Causal Reasoners (arxiv.org)

OctoT2I: A Self-Evolving Agentic Text-to-Image Router (arxiv.org)

Limits of Resolution Equivariance in Fourier Neural Operators (arxiv.org)

Mapping the evolution of small reservoirs in Brazil from 1984 to 2025 using deep learning (arxiv.org)

What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear Regression (arxiv.org)

The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs (arxiv.org)

Demystifying the Optimal Fair Classifier in Multi-Class Classification (arxiv.org)

Don't Ask the LLM to Track Freshness: A Deterministic Recipe for Memory Conflict Resolution (arxiv.org)

GovAI-Pipe: A Layered AI Governance Pipeline for Citizen-Facing AI in Turkey's e-Government Gateway (arxiv.org)

Self-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model Systems (arxiv.org)

GuidaPA: Privacy-Preserving Chatbot for Public Administration via Federated Learning (arxiv.org)

Early Diagnosis of Wasted Computation in Multi-Agent LLM Systems via Failure-Aware Observability (arxiv.org)

MESA: Improving MoE Safety Alignment via Decentralized Expertise (arxiv.org)

How Neural Losses Shape VAE Latents (arxiv.org)

CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts (arxiv.org)

LASER: Loss-Aware Singular-value Decomposition and Rank Allocation for Efficient Low-Precision Vision-Language Models (arxiv.org)

Spatiotemporal Multi-Task Graph Transformer for Trip-Level Transit Prediction (arxiv.org)

FlowTime: Towards Continuous Generative Watch Time Prediction via Flow-based Personalized Priors (arxiv.org)

Recognize Your Orchestrator: An Entropy Dynamics Perspective for LLM Multi-Agent Systems (arxiv.org)

Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery (arxiv.org)

SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems (arxiv.org)

ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction Alignment (arxiv.org)

SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback (arxiv.org)

Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulation (arxiv.org)

On the Difficulty of Learning a Meta-network for Training Data Selection (arxiv.org)

On the Recoverability of Causal Relations from Bulk Gene Expression Data (arxiv.org)

Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models (arxiv.org)

Interpretable Policy Distillation for Power Grid Topology Control (arxiv.org)

Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction (arxiv.org)

Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain (arxiv.org)

Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures (arxiv.org)

The Assistant as a Privileged Persona: A canonical reference in cross-persona self-recognition (arxiv.org)

WildCat: Near-Linear Attention in Theory and Practice (arxiv.org)

Collaborative and Efficient Fine-tuning: Leveraging Task Similarity (arxiv.org)