Microsoft

Least privilege for AI agents: Identity, access, and tool binding

As AI agents become more autonomous, strong identity, access, and auditing controls are critical to keeping them secure.
InfoQ

Google's Genkit Ships Agents API with Detached Turns and Human-in-the-Loop for TypeScript and Go

Google released the Genkit Agents API in preview for TypeScript and Go. The open-source framework packages message history, ...
Tech Times

Ant Group’s Open-Source Robot Brain Beats pi0.5 Across 20 Hardware Types

Cross-embodiment robot AI model LingBot-VLA 2.0, released open source by Ant Group’s Robbyant on July 8, controls 20 distinct ...
IEEE

PreEduAI: A Multi-Agent Collaborative Framework for Automated Preschool Curriculum Development

Abstract: Early childhood education faces significant challenges in developing developmentally appropriate and engaging curricula that meet diverse learning needs, while existing AI-supported ...
IEEE

LLM-Based Multi-Agent Framework for Automated Optical Network Optimization and Planning

Abstract: This paper proposes a Large Language Model(LLM)-based multi-agent framework for automated optical network optimization and planning. The framework leverages DeepSeek-R1 with ...