AI News

Self-complementary completions on six vertices (arxiv.org)

Steering Equilibrium Selection in Regularized Self-Play via the Reference Policy (arxiv.org)

Contagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems (arxiv.org)

Rethinking Multi-Agent Collaboration: When More Is Less (arxiv.org)

Steering Equilibrium Selection in Regularized Self-Play via the Reference Policy (arxiv.org)

HyperAMS-Net: Adaptive Multi-Scale Spatial Hypergraph Network for Brain Disorder Classification (arxiv.org)

Federated Learning Framework for Privacy-Preserving Kidney Stone Detection (arxiv.org)

Personalized Federated Hierarchical Gaussian Processes for Privacy-Preserving Modeling of Heterogeneous Distributed Systems (arxiv.org)

ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzers (arxiv.org)

AutoData: Agentic Search for Pre-training Data Selection (arxiv.org)

LearnActCoder: Role-Aware Error Memory for Adaptive Clinical Coding Agents (arxiv.org)

FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA (arxiv.org)

When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models (arxiv.org)

EmbodiedMind: Adaptive Data Curation and Prefix-Tree Reinforcement Learning for Efficient Embodied Intelligence (arxiv.org)

PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving (arxiv.org)

Well-posedness of neural turbulence closures and tangent dissipation (arxiv.org)

UniExo: Unified Multi-Skill Policies for Musculoskeletal Locomotion and Co-Adaptive Exoskeleton Control (arxiv.org)

The Output-Space Hypothesis: Enumerative Equivalence Checking for Tensor Programs (arxiv.org)

Replan, Repair, or Edit? A Unified Empirical Evaluation of Travel Agents for Itinerary Revision under Resource Disruptions (arxiv.org)

ScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AI (arxiv.org)

Reach or Solve? Attributing Agentic RL Gains with Checkpoint Handoffs (arxiv.org)

From Intent to Action: Benchmarking LLM Safety in Vehicle Voice Command Authorization (arxiv.org)

Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models (arxiv.org)

Efficiently Linking Unstructured Data for Multi-step Reasoning (arxiv.org)

Predict Before You Deploy: Offline Prediction of Quantization-Induced Task Degradation for World Action Models (arxiv.org)

Deep Learning Detection of Beyond-General-Relativity Deviations in Gravitational-Wave Signals: A Detection-Threshold Study with Real LIGO Noise (arxiv.org)

AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment (arxiv.org)

PAPC: Platform Mediation for Privacy-Propagation Externalities in AI-Mediated Workflows (arxiv.org)

Beyond Depth Truncation: Controlled Evaluation of Depth Utilization in Recursive Language Models (arxiv.org)

MaSCoD: A Multi-Agent Framework for Structural-Context-Guided Candidate Causal Graph Generation (arxiv.org)

TorchCraft: Unified binder design by inverting an all-atom structure predictor (arxiv.org)

dQwen3.5: Hybrid-Attention Diffusion Language Models (arxiv.org)

Amortizing Physics-Informed Neural Solvers via Graph Hypernetworks (arxiv.org)

REARL: A Closed-loop Autonomous Driving Simulation Enhancement Framework with Real Traffic Data and Large Language Models (arxiv.org)

Not All AI Agents Are Equal: Characterizing Resource and Performance Dynamics (arxiv.org)

Neuro-Symbolic Agentic AI for Networked Low-Altitude UAVs (arxiv.org)

Customizable and Jointly Optimized Route Planning: A Deep Architecture Enabling Differentiable Shortest-Path Search (arxiv.org)

Accuracy Is Not Enough: A Cross-Architecture Audit of Demographic Bias in Deep Knowledge Tracing (arxiv.org)

How Far Can Sub-3B Open Language Models Go in Zero-Shot Essay Scoring on an 8 GB Consumer GPU? (arxiv.org)

Online Adaptive Kernel Mixing for Gaussian Process Decision Making (arxiv.org)

Uni-LaDiR: Latent Diffusion Unifies Multimodal Reasoning (arxiv.org)

Improving Online Reinforcement Learning via Bidirectional Behavior Prior Distillation (arxiv.org)

Placement Is Free, Composition Is Not: The Latin Square as a Provably-Balanced Construction for Heterogeneous Sequence-Mixer Stacks (arxiv.org)

AURA: Adaptive Uncertainty-Routed Analysis for Email Threat Detection (arxiv.org)

Pretrained Medical Representations for the Practical Screening of Drug Repositioning Candidates (arxiv.org)

Digital Twins for Opinion Dynamics: A Generative LLM Framework for Social Networks (arxiv.org)

Expected Hypervolume Maximization for Multiobjective Optimization under Uncertainties (arxiv.org)

Beyond Flattened Tokens: Structure-Preserving EEG Decoding with Reusable TriDim Blocks (arxiv.org)

A Scalable Trust Discovery Architecture for the Internet of Agents (arxiv.org)

MATCH: Model-Aware Tool Learning with Curriculum Scheduling and Hierarchically Gated Rewards (arxiv.org)