AI News

From AGI to ASI (arxiv.org)

Deployment-Centered Evaluation: Predicting Query-Level Rejection Risk in a Clinical LLM System (arxiv.org)

DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks (arxiv.org)

HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness (arxiv.org)

Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior (arxiv.org)

Benchmarking AI Agents for Addressing Scientific Challenges Across Scales (arxiv.org)

Reducing the Complexity of Deep Learning Models for EEG Analysis on Wearable Devices (arxiv.org)

Prefill Awareness in Large Language Models (arxiv.org)

Constructing Evaluation Datasets for Procedural Reasoning: Balancing Naturalness, Grounding, and Multi-Hop Coverage (arxiv.org)

Teach-and-Repeat: Accurately Extracting Operational Knowledge from Mobile Screen Demonstrations to Empower GUI Agents (arxiv.org)

GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models (arxiv.org)

Topical Phase Transitions in Artificial Intelligence Research: Large-Scale Evidence and an Early-Warning Signature for Emerging Topics (arxiv.org)

Fantastic Scientific Agents and How to Build Them: AgentBuild for Rietveld Refinement (arxiv.org)

(Human) Attention Is (Still) All You Need: Human oversight makes AI-assisted social science reliable (arxiv.org)

Can I Buy Your KV Cache? (arxiv.org)

IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing (arxiv.org)

A Quantitative Experimental Repeated Measures Study of Training Dynamics in a Small Llama Style Language Model Under a Compute-Aware Token Budget (arxiv.org)

MiniMax Sparse Attention (arxiv.org)

Optimizing Appliance Scheduling for Solar Energy Management Using Metaheuristic Algorithms (arxiv.org)

Evaluation Sovereignty in Metadata-Driven Classification: A Multi-Track Framework for Weakly Supervised Information Systems (arxiv.org)

Why Sampling Is Not Choosing: Intentionality, Agency, and Moral Responsibility in Large Language Models (arxiv.org)

CloudCons: A Comprehensive End-to-End Benchmark for Cloud Resource Consolidation (arxiv.org)

Uncertainty-Aware Hybrid Retrieval for Long-Document RAG (arxiv.org)

Is It You or Your Environment? A Bayesian Inference Framework for Genomically-Anchored Personalized Physiological Interpretation (arxiv.org)

A Three-Layer Framework for AI in Scientific Discovery (arxiv.org)

Multiagent Protocols with Aggregated Confidence Signals (arxiv.org)

Multi-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided Dispatch (arxiv.org)

Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday Reasoning (arxiv.org)

AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility (arxiv.org)

Beyond Runtime Enforcement: Shield Synthesis as Defensibility Analysis for Adversarial Networks (arxiv.org)

Before You Think: System 0, AI-Mediated Cognition and Cognitive Colonization (arxiv.org)

EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery (arxiv.org)

Agents-K1: Towards Agent-native Knowledge Orchestration (arxiv.org)

Automated reproducibility assessments in the social and behavioral sciences using large language models (arxiv.org)

AI SciBrief as a Gateway to Research: A Framework for Onboarding Students into New Research Areas (arxiv.org)

GeoDial: A Multimodal Conversational Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns (arxiv.org)

The AI Legal Specialist: A Juridically Autonomous Professional Profile for AI Governance (arxiv.org)

Eigenism: Ethics for a Human-AI Future (arxiv.org)

Creating and Evaluating K-12 GenAI Assessment Graders Through Context Engineering (arxiv.org)

The Challenges of Balancing AI Compliance and Technological Innovations in Critical Sectors: A Systematic Literature Review (arxiv.org)

AI-Automation Tooling in Computer Engineering Education: Mixed-Methods TAM/UTAUT Evidence for a General Acceptance Attitude (arxiv.org)

Boosting Direct Preference Optimization with Penalization (arxiv.org)

Mapping AI Programs in the U.S: A Status Report from Early 2026 and an Analysis of AI Majors and Minors (arxiv.org)

Muse Spark Safety & Preparedness Report (arxiv.org)

Will AI Agents Free Us From Meaningless Work? A Human-Centered Analysis (arxiv.org)

Algorithmic Constitutionalism (arxiv.org)

Position: Generative Engine Optimization Creates Underexamined Risks, Governance Must Target Concentration, Disclosure, and Academic Blind Spots (arxiv.org)

MP3: Multi-Period Pattern Pre-training forSpatio-Temporal Forecasting (arxiv.org)

NaturalFlow: Reducing Disruptive Pauses for Natural Speech Flow in Simultaneous Speech-to-Speech Translation (arxiv.org)

Select and Improve: Understanding the Mechanics of Post-Training for Reasoning (arxiv.org)