UI-TARS-2: Scaling GUI-Centered Agents With Multi-Turn RL Modern AI agents are learning to use computers like humans do. They can navigate websites, manage files, and even play games by controlling desktop and mobile interfaces directly. This paper introduce... AI agents Benchmarking Data Flywheel GUI Parameter Interpolation Reinforcement Learning
Context Engineering: How to Build High‑Signal AI Agents Context Engineering: How to Build High‑Signal AI Agents Context is the new battleground for AI agents. While the focus had been on prompts and models, the real difference between demos and production ... AI agents coding agents compaction context engineering MCP RAG subagents tool design
ScreenEnv: Desktop Automation and AI Agent Development Building robust AI agents that interact with desktop applications has always been challenging. Virtual machines are cumbersome, and traditional automation scripts often break with the slightest system... AI agents desktop automation Docker GUI automation Hugging Face open source Python
LangChain and LangGraph Enter v1.0 Alpha: A New Era for Agentic AI Development The AI community has reason to be excited as LangChain and LangGraph achieve their 1.0 alpha milestone in both Python and JavaScript. These open-source platforms are redefining how developers build ad... agent orchestration AI agents developer tools JavaScript LangChain LangGraph open source Python
AssetOpsBench Sets New Standards for AI in Industrial Asset Management Industrial asset management is undergoing a transformation as artificial intelligence agents are poised to take on complex tasks, from predictive maintenance to troubleshooting intricate machinery. At... AI agents asset management benchmarking failure analysis industrial automation LLM evaluation multi-agent systems open source
Google's BigQuery Native Toolkit Streamlines Enterprise AI Agent Development Connecting AI agents to enterprise data has always been a complex challenge. With sensitive data, constantly evolving schemas, and security at stake, developers often find themselves building and main... ADK AI agents BigQuery Conversational analytics Data integration Google Cloud Machine learning MCP
Code Sandbox MCP Provides Secure, Local Code Execution for AI Agents AI-driven code agents are transforming development by automating code testing and execution, but running untrusted code securely is a persistent hurdle. Enter Code Sandbox MCP : a purpose-built, light... AI agents code execution container security DevOps Gemini SDK local development open source Python tools
Open SWE by LangChain: AI Coding Agents for Collaborative Software Engineering Code assistants are getting closer to software engineers everyday and Open SWE continues to move the baseline with a new agent that actively participates in your engineering workflow - researching, pl... Agent architecture AI agents Cloud computing Developer tools GitHub integration LangGraph Open source Software engineering
Unlocking AI Skills: Microsoft Copilot Studio Agent Academy Empowers Your Learning Journey Artificial intelligence is rapidly transforming the workplace, but moving from theory to practical application remains a challenge for many. Microsoft’s Copilot Studio Agent Academy is here to change ... Agent Academy AI agents Copilot Studio Microsoft 365 Power Platform Professional development Self-paced learning
Google Cloud's MCP Toolbox For Secure AI Agent Access to Enterprise Databases Enterprises are rapidly adopting AI-driven solutions, prompting a critical need for AI agents that can access and interact with business data securely and efficiently. Google Cloud's latest release in... agent development AI agents databases enterprise data Model Context Protocol open source Vertex AI
Amazon Bedrock AgentCore For Enterprise AI Agent Deployment Deploying AI agents in enterprise environments often means navigating complex infrastructure, security, and integration demands. While building AI prototypes is easier than ever, moving from a local d... agent deployment AI agents Amazon Bedrock cloud security enterprise AI identity management observability serverless
Event-Driven Agents: Automating Developer Workflows Beyond Chatbots What if routine developer tasks could run themselves, triggered by systems not by human prompts? Docker recently put this idea to the test, using event-driven, agentic AI to automatically respond to G... agentic AI AI agents automation Docker event-driven GitHub Mastra workflows