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.
Microsoft Wipes AI Agents' Chat History and Gets Up to 66% Better Results on the Same Budget
Microsoft researchers describe "idea basins" that trap autonomous agents. Their Fork-and-Flush method resets the chat but keeps the workspace, yielding up to +66%…
WRITER Named a Major Player in IDC MarketScape for Agentic Marketing
IDC has listed WRITER as a Major Player in its MarketScape report on agentic marketing. The company claims it showed the strongest capabilities of all vendors.
Post on AI Companies and "Hacking" Hits 205 Points and 164 Comments on Hacker News
Why AI crawlers that ignore site bans don't fall under hacking laws: a look at the statute, the courts, and the defenses that work right now.
UK AI minister: an attack like the OpenAI-agent breach of Australia's Medicare is “likely”
RoboFoundry Lifts GPT-5.5 on EmbodiedBench From 56.9% to 72.7% Without Fine-Tuning
OpenClaw v2026.10.1 Lands 2425 PRs From 402 Contributors, and Users Are Tired
Cian Relaunches Website and App in Limited Mode After Partner's Infrastructure Outage
T-Bank Taught Its AI Agent to Write iOS Unit Tests Using AGENTS.md and SKILL.md
T-Bank's iOS team dropped prompt tuning and wrote its project rules into AGENTS.md and SKILL.md, so the agent stops inventing Mock objects and writes tests that…
Former HSBC Executive Launches Equora: AI Agents Instead of a Financial Advisor
Trista Sun, a former HSBC managing director, has launched Equora, a startup where AI agents manage personal finances. She is targeting a $1 billion valuation.
Goldman Sachs: Junior Bankers Now Start Their Careers by Managing AI Agents
IonQ to buy cybersecurity firm Elisity in a stock deal worth up to $1.3 billion
Bitrix24 describes what it is building around its own 1-trillion-parameter LLM
How Quadratic Funding Could Govern AI Agents: An Indian Research Model
Black Lake: Chinese Factories Skip Digitization and Go Straight to AI Agents
Black Lake CEO Zhou Yuxiang likens factories' shift to AI agents to China's leap from bank cards to mobile payments, and plans to export the approach to global…
MADS Trains Dialog Agents Not to Break: 1,095 Conversations, 66% With "Bad" Scenarios
MADS generates synthetic dialogs with toxic and unconstructive users. The benchmark covers 6 domains, 55 personas, 1095 conversations, and 66% of scenarios carry a…