DeepMath: A lightweight math reasoning Agent with SmolAgents

Google stellt Gemini 3 Pro vor: Agenten für multimodale Aufgaben

LLM-Agenten adaptieren live: Neue Testzeit-Methoden steigern Generalisierung

How to Build a Model-Native Agent That Learns Internal Planning, Memory, and Multi-Tool Reasoning Through End-to-End Reinforcement Learning

Dane Stuckey (OpenAI CISO) on prompt injection risks for ChatGPT Atlas

Crucible: Quantifying the Potential of Control Algorithms through LLM Agents

Meet LangChain’s DeepAgents Library and a Practical Example to See How DeepAgents Actually Work in Action