AI News

Adversarial Test-Hardening for AI-Written Code: An Instrument Autopsy and a Pre-Registered Causal Estimate of the Critic Loop (arxiv.org)

Learning Reusable Hybrid Motion Priors for Humanoid Locomotion from Motion Imitation (arxiv.org)

Calibrated Tree-Neural Fusion for Fine-Grained Vegetation Community Classification (arxiv.org)

Distributional Random Forests for Complex Survey Designs (arxiv.org)

Real2Sim2Real for Vision-Language-Action Manipulation: An AMD ROCm-Based Pipeline (arxiv.org)

Spatial Prediction of Soil Microplastics and Organic Matter Using Graph Attention Networks (arxiv.org)

MEMENTO: Memory-Guided Memetic Code-as-Policy Evolution (arxiv.org)

Nearly Tight Bounds for Cross-Learning Contextual Bandits with Graphical Feedback (arxiv.org)

Flick: Few Labels Text Classification using K-Aware Intermediate Learning in Multi-Task Low-Resource Languages (arxiv.org)

An Agentic Orchestration of Atomistic Simulations (arxiv.org)

Building AI That Works: ESnet's Pragmatic Approach to AI-Driven Operational Excellence (arxiv.org)

Do Visual Features Improve Other-Initiated Repair Detection? A Dyadic Multimodal Approach (arxiv.org)

Hierarchical Grading in Large Language Models (arxiv.org)

Charging Phase Health Indicators for Battery State-of-Health Estimation: A Systematic Comparison of CC, CV, and Combined Approaches under Cross-Battery Validation (arxiv.org)

HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answering (arxiv.org)

CALMRec: Causally Aligned Language Memory for Long-Horizon Recommendation (arxiv.org)

ACM: Agentic Context Management for Long Horizon Tasks (arxiv.org)

A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever (arxiv.org)

Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents (arxiv.org)

Evaluating and Mitigating the Misguidance Effect of Buggy Code in LLM-Generated Unit Tests (arxiv.org)

Copula Based Fusion of Clinical and Genomic Machine Learning Risk Scores for Breast Cancer Risk Stratification (arxiv.org)

TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation (arxiv.org)

Invariant Discovery for Networked Systems (arxiv.org)

An Empirical Study of Feature Selection Granularity (arxiv.org)

MS-GPT: Rethinking MS/MS De Novo Structure Elucidation as Spectrum-Induced Posterior Querying of a Molecule-Language Model (arxiv.org)

Short-Term Pain for Long-Term Gain: Adaptive Experiment with Post-Commitment Reward Shift (arxiv.org)

Where Is the Cost of Third-Party API Routers in Agentic Software Development? (arxiv.org)

Frustratingly Simple Black-Box Adaptation of Language Models via Logit Bias (arxiv.org)

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks (arxiv.org)

Choosing a Text Embedding Model: A Practical Benchmarking and Decision Framework (arxiv.org)

Do Small Models Use the Law You Give Them? Context-Injected Fine-Tuning for Legal QA in Bangladesh (arxiv.org)

Physics-Informed Neural Networks for Discovering Periodic Orbits in the Gravitational Three-Body Problem (arxiv.org)

Plans Work in Mysterious Ways: Evaluating a Plan Mode for Spreadsheet Agents (arxiv.org)

Novel Claim or D\'ej\`a Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking (arxiv.org)

GFLAN: Generative Functional Layouts (arxiv.org)

Adaptive Data Admission and Retention for Streaming Federated Learning (arxiv.org)

A Fixed-Effects Causal Forest for Staggered Adoption, with an Application to Medicaid Expansion (arxiv.org)

Between Suppression and Collapse: Evaluating Narrative Unlearning with LENS (arxiv.org)

Quotient Tree Arithmetic: Deferred-Division Computation with Bounded Symbolic Depth and Cross-Subtree Cancellation (arxiv.org)

Variational-Ising-Attention (VIA):TailoredAttentionMattersfor Science (arxiv.org)

When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost (arxiv.org)

K-Survival Means (arxiv.org)

PathScale-R1: Cross-scale Reasoning for Pathological Image Analysis (arxiv.org)

A Survey of Graph Transformers: Architectures, Theories and Applications (arxiv.org)

EmotionAI: A Privacy-Preserving Computational Intelligence Pipeline for Speech-Emotion-Grounded Conversational Analysis (arxiv.org)

Probabilistic Symbolic Regression for Equation Discovery via Operator-induced and Regularized Symbolic Forests (arxiv.org)

BHARATI: Morphology-Aware Tokenizers for Classical Indian Languages with Subword Fertility Analysis (arxiv.org)

Falsifiable Commitment Planning for Self-Correcting Web Agents (arxiv.org)

xMIx: High-Performance Serving-Time Platform for Mechanistic Interpretability Apps (arxiv.org)

Semalith v1.4: A Calibrated 184M Safety Classifier Achieving State-of-the-Art Prompt-Injection Detection at 44x Fewer Parameters than Llama-Guard-3-8B (arxiv.org)