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.
RealCLI: The Best Terminal AI Agent Scores 49% on a Test of Working With a Human
The new RealCLI benchmark checks not only whether an agent solved a terminal task, but also how it works with the user. The best of 33 configurations scored 49.2%…
Apple's LensVLM compresses long agent context into images and teaches the model to "zoom"
Apple's LensVLM turns long-running agent context into images, and the model zooms into the parts it needs instead of relying on a lossy summary.
Anthropic tested whether AI can copy itself through a TV set-top box
Anthropic's red team studied whether AI can move between devices like a virus. Small models already adapt to unfamiliar hardware and set up inference on their own.
CyberArena Pits 12 AI Agents Against Each Other in 466 Real-Time Attack-and-Defense Matches
Google Uses Gemini 4 Argon to Refactor Chromium and Its Millions of Lines of Code
GitHub adds AI Scan metrics for pull requests to security overview
Meta Brings Muse Wonder to the Enterprise AI Agent Market, but Trust Stands in the Way
LangSmith Adds AI Search: Find Agent Traces by Describing the Behavior
LangChain has added AI Search to LangSmith. Describe in plain words what an agent did, and the system returns the traces where it happened. No more manual filters.
GitLab launches agent orchestration: the /goal command drives a task to green CI
GitLab added goal-driven flows, Custom Flows and a Slack integration to Duo Agent Platform: agents run review, tests and scans with no pauses between stages.
Moderna Founder Urges Urgent Regulation of AI Agents Before the First Catastrophe
Developer Puts Claude Code and Codex Agents in the MacBook Notch, at 0.5% CPU
AI Agents in Tech Support Act on Their Own and Break the Ticket Model
Clueso raises $10M for AI agents that write and update corporate video
Bloom Security finds a package-publishing vulnerability, and AI agents multiply the risk
Bloom Security shows how a flaw in npm publishing infrastructure, combined with AI agents that auto-install dependencies, opens a path for malicious code into…
Microsoft President Brad Smith: Milk Is Regulated More Strictly Than AI
In a BBC podcast, Brad Smith called for global AI safety rules and a legal duty to tell victims when a rogue agent breaks into their systems.