Agent Skills Can Be Harmful: An Empirical Study of Skill-Induced Failures in LLM Agents
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
CoQui: A Coordinate-Conditioned Quantum Implicit Generative Adversarial Network for End-t…
Wintermute Plans $1 Billion AI Investment to Compete on Wall Street
ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM…
New York City Probes Prediction Markets Over Ads, Social Harms
Google Pixel 11 launch: Live updates as the company unveils new devices, AI features and …
Forward and Inverse Virtual Metrology for Phototransistor Gain: A Hierarchical, Uncertain…
Small-Scale Experiments: Are We There Yet?
LookBack: Where and How to Score LVLM Responses via Visual Reference Usage
AI Coding Startup Lovable Raises $400 Million at $13.3 Billion Valuation
You’re Thinking About Online Trends All Wrong
Air Quality Station Simulation via LSTM and Attention-Based Modelling
GeoBridge: Decoupled Semantic Conditioning for Generative Image Geolocalization
Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling
Tech Investments Boost Norway's Sovereign Wealth Fund
Located but Not Releasable: Silent Gate Inversion and Bounded Linear Release
SpaceXAI launches Grok Bot, an always-on AI agent
This $200 AI app turns your spoken words into polished writing
CoDiR: Confidence-Guided Diffusion Refinement for Semi-Supervised Histopathology Segmenta…
Hybrid Gated Attention
Towards Model-based Run-time Cybersecurity: On Control-Flow Anomaly Detection, Attack Ide…
Tencent Sales Top Estimates on WeChat Ad Surge, Resilient Games
Toward Meaningful Transparency for AI Chatbots: Disclosing Persuasive Intent Reduces Pers…
High-Order Liquid Evidence Encoding for Gradual GNSS Spoofing Detection in Autonomous Dri…
GRPO for Financial Advice Generation: Outperforming Commercial LLMs under CATE Evaluation
Language-Conditional Dequantization: Recovering What Quantization Steals from Non-English…
TradingMoE: Routing the Right Experts in Evolving Markets
VOLA: Improving Open-World Driving by VLM-Based Semantic Attribute Prediction
The Sleeping Agent: What Gist-Based Context Compression Loses and Why
Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction