Illusions of reflection: open-ended task reveals systematic failures in Large Language Models' reflective reasoning

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding

Microsoft AI Introduces rStar2-Agent: A 14B Math Reasoning Model Trained with Agentic Reinforcement Learning to Achieve Frontier-Level Performance

Comparing the Top 6 Inference Runtimes for LLM Serving in 2025

LLM-Inference auf IoT: Adaptive Split-Computing reduziert Speicher und Latenz

Unternehmensvorstände fordern KI-Produktivität, doch sie erhöhen die Angriffsfläche

LLMs Position Themselves as More Rational Than Humans: Emergence of AI Self-Awareness Measured Through Game Theory