Learning to Configure Agentic AI Systems
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
Neutralizing Popularity Bias in LLM-based Recommendation via Counterfactual Reasoning Gui…
Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Met…
NOAH: Learning the Full Patient Journey. A Longitudinal Multimodal Time-Aware Model for R…
SAGE: A Hierarchical Framework for Evaluating Interpretive Literary Quality in Narratives
SWE-Test: Benchmarking LLM Vulnerability Discovery via Input Prediction
AgentLeak: Cloning Stronger LLM Agent Capabilities onto Weaker Agents Beyond Skill Steali…
Omni Interaction Agent Technical Report
SQLMorph: Query Mutation and Fine-Grained Metrics for Text-to-SQL Evaluation
Transformers as In-Context Samplers: From Closed-Form Diffusion to Estimation-Free Sampli…
Hi-FLoop: Hierarchical State-Feedback Loops for Multi-Timescale World Modeling
Silent Revision: Measuring Undisclosed Change in the Safety Frameworks of Frontier AI Dev…
Earth System World Model for What-If Simulations: A Case Study for Terrestrial Ecosystems
Fewer yet critical: Reducing Redundant Token Dependencies for Transformer-based Time Seri…
BIFTA: Brain-Inspired Few-Shot Tactile Adaptation for Unknown Sensors
MoEMB: Scaling Universal Multimodal Embeddings with Efficient Mixture-of-Experts Models
Neither Adversarial Training Nor Purification: Emergent Adversarial Robustness from Oscil…
NormViz: A Benchmark and Framework for Grounding Multimodal Reasoning in Global Cultures
Hyperparameter Scaling Laws Across MoE Sparsity
It Is Not My Code Anymore
Simulating the Marginal Green Contribution of AI Modules in a Smart-Agriculture Platform:…
Evaluating Deep-Search Agents under Hierarchical Web Evidence Poisoning
Formation of structural attractors in neuromorphic systems
Monte Carlo-Based Ex-Ante Assessment of the Green Benefits of an AI-Driven Smart Agricult…
We Built a Mirror and Mistook It for a Mind: Causal Liability and the Fallacy of AI Consc…
Improving Proficiency and Efficiency of Android GUI Agents via Self-Generating Tool Actio…
TriCCOT: Tri-part Convolutional Conformal Transformer for Onboard Space Object Detection
RedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context Serving
EEG-Driven Decoding Framework for Passenger Hazard Perception in Highly Automated Vehicles
Learning transferable human physiology from two million hours of sleep with SleepFM-2