Tag: Multi agent systems

Google DeepMind publishes AI agent security roadmap

Google DeepMind published its AI Control Roadmap on June 18, 2026 — a framework defining how to systematically detect and block unwanted AI agent behaviors inside the company's infrastructure. The firm analyzed one million coding agent trajectories to build a real-time monitoring system grounded in production data.

MCP solved tool calling, A2A solved coordination. What solves transport?

MCP won the tool-calling layer, A2A won task coordination between agents. But the P2P transport problem for AI agent networks remains unsolved. An analysis of the protocol stack and a consolidation forecast.

LLM Self-Improvement Systems — How a Model Learns to Train Itself

A new survey from the Zesearch NLP Lab (Stony Brook University) frames LLM self-improvement as a closed loop: the model acquires its own data, evaluates its own outputs, and updates its parameters. We explain how the loop works, what the GRO framework is, and where the real limits of this approach lie.

RecursiveMAS: AI agents communicate without tokens — 2.4× faster, 75% cheaper

Researchers from UIUC and Stanford developed RecursiveMAS, a framework that lets AI agents exchange information through embedding space instead of text. The result: 2.4× faster inference and 75% fewer tokens consumed.

Google Announces Gemini Enterprise Agent Platform at Cloud Next '26 in Las Vegas

Google has announced at the Cloud Next '26 conference in Las Vegas a new platform that entirely replaces Vertex AI as the central environment for building and deploying AI agents in enterprises. Gemini Enterprise Agent Platform has been available since April 22, 2026, and from that point takes over all further updates and development plans for Vertex AI.

Anthropic uruchamia Claude Managed Agents. Koniec z miesiącami pracy nad infrastrukturą agentów AI

Meta przejmuje Moltbook: „Martwa sieć” staje się poligonem dla agentów AI