AI Agents
AI agents are LLM-powered systems that don't just answer — they plan steps, call tools and drive a task to completion: writing code, searching the web, booking, analyzing. 2026 became the year of agents, from coding agents to autonomous researchers. This page gathers all our coverage of agentic AI: launches, protocols (MCP, A2A), reliability and real-world use.
Hexo Labs Published SIA — an Agent That Updates Itself During Operation
Hexo Labs released the open source code for SIA — a system that improves itself by updating both the agent's instructions and the weights of
IBM and Artificial Analysis create benchmark: AI agents fail at IT tasks
Large language models scored less than 50% on the new ITBench-AA benchmark for assessing AI agents' ability to solve corporate IT tasks. Thi
Cursor Revealed Lessons from a Year of Developing Cloud AI Agents
GitLab Expanded Support for Open-Source Models for Closed Networks
SIMA 2 from DeepMind: The First Thinking Agent for Video Games and Robotics
GitLab Automates Full Merge Request Lifecycle with Developer Flow
DeepMind Presented Co-Scientist — Multi-Agent AI for Accelerating Scientific Research
DeepMind created a multi-agent AI assistant based on Gemini that helps scientists generate hypotheses and find new solutions for rare diseas
How Replit Agent Solves User Loss Problem with a Single Prompt
Replit introduced automatic authentication integration for apps: the agent will create a login system in one prompt so apps no longer lose u