Improving Proficiency and Efficiency of Android GUI Agents via Self-Generating Tool Actio…
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Monte Carlo-Based Ex-Ante Assessment of the Green Benefits of an AI-Driven Smart Agricult…
Simulating the Marginal Green Contribution of AI Modules in a Smart-Agriculture Platform:…
CIVI: A Framework for Diagnosing Search Agent Failures in Civic Information
Risk Is Not Review Value: Wrong-Answer Exposure Under Bounded Review Budgets
From Concentration to Differentiation and Back: Routing Effective Rank in MoE Reasoning C…
Safety boundary maintenance in consumer AI systems responding to pediatric health queries…
Causal Attribution for Agentic Decisions: Estimators, Coupling, and a Traceability Specif…
We Built a Mirror and Mistook It for a Mind: Causal Liability and the Fallacy of AI Consc…
EEG-Driven Decoding Framework for Passenger Hazard Perception in Highly Automated Vehicles
Predicting Wind Turbine Power Using Machine Learning and Weather Forecasts
Quantile-Led Feature Extraction for Multi-Horizon Predictive Maintenance in Industrial Ma…
Modus Tollens and Counterfactuals and Counterfactual Reasoning Based on Three Types of Ne…
DAREBench: Deployment-Aware and Reliable Evaluation of Models as Agents
Generator-Independent Runtime Assurance under Partial Observation
Generating Instance Generators in PDDL Planning
SCIRIGOR:Evaluating Open-Ended Scientific Analysis Beyond Final Scores
A visual large language foundational model for medical image recognition using clinician-…
AutoKD: Autonomous Knowledge Discovery
When and Why LLM Causal Priors Help: Closed-Loop Prior Selection for Amortized Causal Inf…
Exposing Weaknesses in Emotion Recognition in Conversations
Distilling Vision-Language Models for On-Device Fire Understanding
More Than Mimicking Reviewers: Evaluating LLMs for Pre-Submission Peer Review
Beyond Final Decisions: A Process-Centric Benchmark for Transparent AI-Assisted Peer Revi…
Learning Counterfactual World Models for Embodied Reasoning under Partial Observability
AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories
Agentic Pressure: The Endogenous Entropy of Reliable Autonomy
Building Trustworthy Graph-Agentic RAG for Social Good: Architectures, Failure Propagatio…
Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expert…
What LLM Trading Agents Actually Do in Production: A Six-Month, Population-Scale Record f…