InfoQ Homepage Agents Content on InfoQ
-
GLM-4.5 Launches with Strong Reasoning, Coding, and Agentic Capabilities
Zhipu AI has released GLM-4.5 and GLM-4.5-Air, two new AI models designed to handle reasoning, coding, and agent tasks within a single architecture. They use a dual-mode system to switch between complex problem-solving and faster responses, aiming to improve both accuracy and speed.
-
Microsoft Releases A2A .NET SDK for Building Collaborative AI Agents
Microsoft has released the A2A .NET SDK, a new developer toolkit that enables building AI agents capable of communicating and collaborating using the Agent2Agent (A2A) protocol. With support for both client and server roles, the SDK allows .NET-based agents to interact with others across ecosystems, regardless of the underlying technology.
-
“A Security Nightmare”: Docker Warns of Risks in MCP Toolchains
A new blog post from Docker warns that AI-powered developer tools built on the Model Context Protocol (MCP) are introducing critical security vulnerabilities — including real-world cases of credential leaks, unauthorized file access, and remote code execution.
-
Google Releases Major Firebase Studio Updates for Agentic AI Development
At Google Cloud Summit London in early July, Google revealed new capabilities in Firebase Studio that promise to enhance agentic cloud-based development: an autonomous Agent mode, native support for Model Context Protocol (MCP), and Gemini CLI integration. These updates aim to streamline agentic AI development by making AI agents more independent and seamlessly embedded in developer workflows.
-
Databricks Agent Bricks Automates Enterprise AI Development with TAO and ALHF Methods
Databricks introduced Agent Bricks, a new product that changes how enterprises develop domain-specific agents. The automated workflow includes generating task-specific evaluations and LLM judges for quality assessment, creating synthetic data that resembles customer data to supplement agent learning, and searching across optimization techniques to refine agent performance.
-
Qwen Team Releases Qwen3-Coder, a Large Agentic Coding Model with Open Tooling
Qwen Team has announced Qwen3-Coder, a new family of agentic code models designed for long-context, multi-step programming tasks. The most capable variant, Qwen3-Coder-480B-A35B-Instruct, is a Mixture-of-Experts model with a total of 480 billion parameters and 35 billion active parameters per forward pass.
-
OpenAI Announces Generalist ChatGPT Agent to Take on Excel, PowerPoint, and Chrome
OpenAI's ChatGPT Agent merges advanced browsing and summarization for seamless data handling. Developers can now generate editable spreadsheets and presentations with simple prompts, integrating outputs directly into productivity tools. With impressive accuracy and connectivity, it enhances workflow efficiency while automating complex tasks, heralding a new era in AI-driven productivity.
-
Amazon Launches Bedrock AgentCore for Enterprise AI Agent Infrastructure
Amazon announced the preview of Amazon Bedrock AgentCore, a collection of enterprise-grade services that help developers deploy and operate AI agents at scale across frameworks and foundation models. The platform addresses infrastructure challenges developers face when building production AI agents.
-
Microsoft Adds Deep Research Capability in Azure AI Foundry Agent Service
Unlock the future of research with Microsoft’s Azure AI Foundry Agent Service, featuring Deep Research—an innovative tool that empowers knowledge workers in complex fields. This advanced AI capability autonomously analyzes and synthesizes web data, automating rigorous research tasks while ensuring traceability and transparency. Sign up for the public preview today!
-
Docker Expands Compose for Agent Development and Ties in Cloud Offload Support
Docker launched a new feature to let developers define, build, and run agents using Docker Compose, with the aim to streamline agent development process and reduce repetitive tasks. Additionally, Docker Offload, now in beta, provides a way to seamlessly offload building and running models to remote GPU compute.
-
Docker Desktop 4.43 Expands Model Runner and Brings New Compose-Kubernetes Bridge
Following the introduction of Model Runner a few months ago, Docker Desktop 4.43 expands its capabilities with improved model management and broader OpenAI compatibility. The release also debuts a new Compose Bridge to simplify the generation of Kubernetes configurations and upgrade the Gordon AI agent.
-
Azure AI Foundry Agent Service Gains Model Context Protocol Support in Preview
Microsoft's Azure AI Foundry Service now supports the Model Context Protocol (MCP), revolutionizing AI agent integration. This streamlined approach eliminates cumbersome custom coding, allowing seamless connection to data sources and workflows. With enterprise-grade security, developers can effortlessly enhance agent capabilities, ushering in a new era of interoperability and efficiency in AI.
-
Google Previews Gemini's Agent Mode in Android Studio Narwhal
Google has announced the integration of Gemini in Android Studio's Agent Mode into the latest canary release of Android Studio, Android Studio Narwhal preview. According to Google, the new Agent Mode is designed to handle multi-step development tasks that span across several files.
-
Teams Toolkit Rebranded to Microsoft 365 Agents Toolkit
Microsoft has introduced the Microsoft 365 Agents Toolkit, a developer framework designed to streamline the creation of AI-powered agents that automate tasks across Microsoft 365 applications. The toolkit provides tools and APIs to build, test, and deploy intelligent agents capable of handling workflows in Outlook, Teams, Word, and other M365 apps.
-
GitHub Unveils Prototype AI Agent for Autonomous Bug Fixing
GitHub unveils a groundbreaking AI coding agent that autonomously identifies bugs and proposes fixes via pull requests, marking a shift towards independent code maintenance. Leveraging advanced semantic analysis and vulnerability libraries, this tool aims to alleviate developers' workload, allowing them to prioritize complex problem-solving.