AI-агенты
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.
IBM Research analyzed where AI agents break down on APIs, documents, and rules in VAKRA
IBM Research's analysis of VAKRA shows that even strong models lose reliability when they have to combine APIs, documents, multi-step reason
Alibaba releases Qwen3.6-35B-A3B — a multimodal MoE model focused on agentic coding
Qwen has released the weights for Qwen3.6-35B-A3B: with 35 billion parameters and 3 billion active, the model works with code, images, and v
Hugging Face published Ecom-RLVE, a training environment for e-commerce AI agents
Hugging Face published Ecom-RLVE, an open-source environment where AI agents learn to handle purchase conversations, use tools, and earn a v
McKinsey outlines four steps to scale agentic AI with high-quality data
Habr AI: eight common complaints about AI models — from hallucinations to agent failures
AWS cut marketing page production from hours to minutes with agentic AI
zymi framework proposes building AI agents like a dbt project with YAML and event sourcing
Cloud.ru named five boring tasks that Big Tech is already handing over to AI assistants at scale
Cloud.ru compiled five categories of corporate routine that businesses are already handing over to AI: from support and code to legal search
BetBoom: AI agents are changing development and forcing engineers to relearn
AI agents are becoming part of real-world development: they speed up reviews and routine work, but at the same time raise security requireme
How a Claude-based Telegram assistant eased the CEO's load and took on part of the team's work
AI agents instead of vibe coding: how an autonomous pipeline takes a task to PR
Yandex Cloud explained how to deploy AI agents in information security without false blocks or disruptions
Why memory has become a key element of AI agents: a breakdown across three levels of complexity
NVIDIA showed how Gemma 4 with voice and a webcam runs on Jetson Orin Nano Super
NVIDIA published a demo in which Gemma 4 decides on its own when to activate the webcam and responds by voice — all locally on Jetson Orin N
OpenAI explained how to configure Codex: personalization, level of detail, and access permissions
OpenAI released a guide to Codex settings: where to enable personalization, how to choose the level of detail for its work, and why, for lon