AI News

JaxAHT: A JAX-Based Library for Ad Hoc Teamwork (arxiv.org)

Degraded but Not Entirely Ineffective: PE-Based Deformable Graph Neural Networks (arxiv.org)

Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models (arxiv.org)

Windowed A-K-MDP (arxiv.org)

Recoverability as a System Primitive for Long-Horizon AI Agents (arxiv.org)

Enhancing Event Candidate Acquisition for Event Linking (arxiv.org)

GeoSkill:Experience-Driven Hierarchical Skill Learning with Collaborative Revision forGeospatialAgents (arxiv.org)

Cost Characterization of Vertically Partitioned Federated Knowledge Graphs (arxiv.org)

FedV-KGQA in Practice: Design Lessons and an Interactive Prototype (arxiv.org)

Safety as a Constraint: Fine-Tuning a LLM Recommender to Explain Itself (arxiv.org)

Solar Intelligence (arxiv.org)

Identity Is More Than Recall: A Benchmark for Persistent Identity in Deployed AI Agents (arxiv.org)

$\tau$-Elicitation: Benchmarking multi-turn entity extraction in voice agents (arxiv.org)

FLoKD: Adaptive Knowledge Distillation for Federated Low-Rank LLM over Wireless Networks (arxiv.org)

How User-AI Mistreatment Occurs and Matters in Conversational Systems? (arxiv.org)

Causal multi-modal AI for personalized chemosensitivity prediction (arxiv.org)

Planning or Learning: Reliability and Cost in Multi-Asset Maintenance (arxiv.org)

A Hybrid Agentic AI Framework for Intelligent Supply Chain Analytics (arxiv.org)

Toward a Decision-Assurance Layer for AI-Assisted Flight Planning in Air Traffic Management (arxiv.org)

AutoTailor: Automatic, User-Aligned Capability Selection and Adaptation for Web Agents (arxiv.org)

Asclepius: An Adaptive Harness for Long-Horizon Clinical Agents (arxiv.org)

From Legal Text to AI-specific Risk Sources: A Systematic Analysis of the EU AI Act's High-Risk Requirements (arxiv.org)

Fraglingo: Molecular Design via Attachment-Aware Autoregressive Fragment Generation (arxiv.org)

OrchSLM: Probing the Dynamics of Small Language Model Orchestration (arxiv.org)

Governing at Machine Speed: An Adaptive Intelligence Architecture for Real-Time AI Policy Enforcement (arxiv.org)

Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures (arxiv.org)

TimeThink: Eliciting Compositional Reasoning in Timeseries Large Language Models (arxiv.org)

LabAgent: Customize Any Research Hubs for Scientific Discoveries Using AI Agents (arxiv.org)

Carbon-Aware Routing for Function Calling in Edge-Cloud LLM Systems (arxiv.org)

Toward Self-Adaptive Physical AI: Can LLM Agents Manage Long-Horizon Physical Tasks? (arxiv.org)

Vibe Patenting: Evaluating LLM Judges for Professional Patent-Drafting Agents (arxiv.org)

Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement (arxiv.org)

ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search (arxiv.org)

Token Efficient Task Execution via Application Behavior Modeling for Web Agents (arxiv.org)

Design of a Deep Learning Credit Risk Early Warning System Integrating Multi-source Heterogeneous Data (arxiv.org)

Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup-Stable-Decay (arxiv.org)

Exact Recovery by Neighborhood Smoothing in Directed Stochastic Block Models (arxiv.org)

Prelimit Coupling and Steady-State Convergence of Constant-stepsize Nonsmooth Contractive SA (arxiv.org)

Neural Operators for Nonlinear Functionals on RKHS (arxiv.org)

Direct Conditional Transition Sampling for Diffusion Inverse Problems (arxiv.org)

Predictive Likelihood Ratios for Language Model Watermark Detection (arxiv.org)

Graph Matching Relaxations and Amortization for Supervised Graph Prediction (arxiv.org)

Stochastic Gradient Descent for Operator Learning in Hilbert Spaces: Convergence Rates and Minimax Lower Bounds (arxiv.org)

Unfair Utilities and First Steps Towards Improving Them (arxiv.org)

Sharp Rates and a One-Line Correction for Spectral Representation Learning (arxiv.org)

Curvature-Independent Regret Bounds for Distributed Online Optimization on Hadamard Manifolds (arxiv.org)

Equilibrium bias and convergence in augmented primal--dual dynamics with sampled constraints (arxiv.org)

On the Equivalence of Stochastic Control and Path Space Formulations for Schr\"odinger Bridges over Compact Connected Lie Groups (arxiv.org)

Modeling Social Dynamics with an LLM-Enabled Agent Based Network-Dynamic (LAND) Model (arxiv.org)

Toward Optimal Switching Regret for Multi-Armed Bandits with Oblivious Adversary (arxiv.org)