InfoQ Homepage Google Content on InfoQ
-
Google Introduces Middleware Architecture for Genkit Applications
Google has introduced Middleware for Genkit, its open-source framework for building AI-powered and agentic applications. The update adds a programmable interception layer around model calls, tool execution, and generation loops, giving developers more control over reliability, safety, and orchestration inside production AI systems.
-
With Android CLI, Google is Making the Android Toolchain Agent-Friendly
Google introduced new Android development tools that enable building apps up to 3x faster by using AI agents, including a redesigned Android command-line interface (CLI), structured skills", and an integrated knowledge base. These tools are designed to support agent-driven workflows and are compatible with third-party agents such as Claude Code and Codex, in addition to Google Gemini.
-
Google New TPU Generation is Specifically Designed for Agents and SOTA Model Training
Google has unvelied a new generation of Tensor Processing Units (TPUs), featuring two specialized chips designed to accelerate model training and agent workflows, which require continuous, multi-step reasoning, and action loops distributed across multiple models. The new TPUs deliver better performance, memory, and energy efficiency, the company says.
-
AWS Interconnect Reaches General Availability with Managed Multicloud and Last-Mile Connectivity
AWS Interconnect reached general availability, offering managed private Layer 3 connections to Google Cloud and a last-mile capability via Lumen. Azure and OCI support is planned for later in 2026. AWS published the underlying specification on GitHub under Apache 2.0, which Forrester analysts read as a play to set a de facto standard for multicloud connectivity.
-
Google Introduces Room 3.0: a Kotlin-First, Async, Multiplatform Persistence Library
Room 3.0 is a major update to Android's persistence library that introduces breaking changes in key areas. The new release focuses on modernizing Android persistence layer around Kotlin Multiplatform and expands platform support to include JavaScript and WebAssembly.
-
Subagents in Gemini CLI Enable Task Delegation and Parallel Agent Workflows
Google has introduced subagents in Gemini CLI, a new capability designed to help developers delegate complex or repetitive tasks to specialized AI agents operating alongside a primary session.
-
Google ADK for Java 1.0 Introduces New App and Plugin Architecture, External Tools Support, and More
Google's Agent Development Kit for Java reached 1.0, introducing integrations with new external tools, a new app and plugin architecture, advanced context engineering, human-in-the-loop workflows, and more.
-
Google’s Aletheia Advances the State of the Art of Fully Autonomous Agentic Math Research
Google announced Aletheia, an AI using Gemini 3 Deep Think that solved 6/10 novel math problems in the FirstProof challenge. Aletheia also scored ~91.9% on IMO-ProofBench, signaling a significant shift in automated research-level proof discovery without human intervention.
-
Google Brings MCP Support to Colab, Enabling Cloud Execution for AI Agents
Google has released the open-source Colab MCP Server, enabling AI agents to directly interact with Google Colab through the Model Context Protocol (MCP). The project is designed to bridge local agent workflows with cloud-based execution, allowing developers to offload compute-intensive or potentially unsafe tasks from their own machines.
-
Google Open Sources Experimental Multi-Agent Orchestration Testbed Scion
Designed to manage concurrent agents running in containers across local and remote compute, Scion is an experimental orchestration testbed that enables developers to run groups of specialized agents with isolated identities, credentials, and shared workspaces.
-
Google Unveils AppFunctions to Connect AI Agents and Android Apps
In a move to transform Android into an "agent-first" OS, Google has introduced new early beta features to support a task-centric model in which apps provide functional building blocks users leverage through AI agents or assistants to fulfill their goals.
-
Google Researchers Propose Bayesian Teaching Method for Large Language Models
Google Research has proposed a training method that teaches large language models to approximate Bayesian reasoning by learning from the predictions of an optimal Bayesian system. The approach focuses on improving how models update beliefs as they receive new information during multi-step interactions.
-
Google Launches Automated Review Feature in Gemini CLI Conductor
Google has enhanced its Gemini CLI extension, Conductor, by adding support for automated reviews. The company says this update allows Conductor "to go beyond just planning and execution into validation", enabling it to check AI-generated code for quality and adherence to guidelines, strengthening confidence, safety, and control in AI-assisted development workflows.
-
Google Explores Scaling Principles for Multi-Agent Coordination
Google Research tried to answer the question of how to design agent systems for optimal performance by running a controlled evaluation of 180 agent configurations. From this, the team derived what they call the "first quantitative scaling principles for AI agent systems", showing that multi-agent coordination does not reliably improve results and can even reduce performance.
-
Firestore Adds Pipeline Operations with over 100 New Query Features
Google has overhauled Firestore’s query engine, introducing "Pipeline operations" that enable complex server-side aggregations and array unnesting. The update shifts Firestore Enterprise toward an optional indexing model, allowing architects to prioritize write speed and lower costs. While it brings parity with MongoDB-style aggregations, the preview currently lacks real-time and emulator support.