InfoQ Homepage Large language models Content on InfoQ
-
OpenAI Introduces Websocket-Based Execution Mode to Reduce Latency in Agentic Workflows
OpenAI introduces a WebSocket-based execution mode for its Responses API to improve agentic workflow performance in coding agents and real-time AI systems. The update reduces latency by up to 40 percent by replacing HTTP request-response cycles with persistent connections, improving streaming, tool execution, and multi-step orchestration in production-scale AI systems.
-
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.
-
Mistral Adds Remote Agents and Work Mode to Le Chat
Mistral has released Mistral Medium 3.5, a 128-billion parameter model designed to handle instruction following, reasoning, and coding within a single system, and introduced new cloud-based agent capabilities in its Vibe and Le Chat products.
-
Cloudflare Builds High-Performance Infrastructure for Running LLMs
Cloudflare has recently announced new infrastructure designed to run large AI language models across its global network. As these models rely on costly hardware and must handle large volumes of incoming and outgoing text, Cloudflare separates the model's input processing and output generation onto different optimized systems.
-
NVIDIA Launches Ising Open Models for Quantum Computing
NVIDIA has announced a new family of open models called NVIDIA Ising, designed to address quantum processor calibration and quantum error correction. These are two of the main engineering challenges limiting the scalability of current quantum systems, where noise and instability in qubits reduce the reliability of computations.
-
Cloudflare Announces Agent Memory, a Managed Persistent Memory Service for AI Agents
Cloudflare announced Agent Memory in private beta, a managed service that extracts structured memories from AI agent conversations and retrieves them on demand using five-channel parallel retrieval with Reciprocal Rank Fusion. Shared memory profiles let teams of agents access common knowledge. Competitors include Mem0, Zep, LangMem, and Letta.
-
How Slack Manages Context in Long-Running Multi-agent Systems
To sustain productivity in long-running agent systems, Slack engineers moved away from accumulating chat logs and started using structured memory, validation, and distilled truth to maintain coherence and accuracy of long-running agent systems.
-
Legare Kerrison and Cedric Clyburn on LLM Performance and Evaluations
Effectively measuring the performance of applications that are leveraging Large Language Models (LLM) is critical to the adoption of AI technologies in organizations. Legare Kerrison and Cedric Clyburn from RedHat team recently spoke at Arc of AI 2026 Conference about practical methods to evaluate and optimize LLM inference.
-
Anthropic Introduces Managed Agents to Simplify AI Agent Deployment
Anthropic introduces Managed Agents on Claude, a managed execution layer for agent-based workflows. It separates agent logic from runtime concerns like orchestration, sandboxing, state management, and credentials. The system supports long-running multi-step workflows with external tools, error recovery, and session continuity via a meta-harness architecture.
-
Designing Memory for AI Agents: inside Linkedin’s Cognitive Memory Agent
LinkedIn introduces Cognitive Memory Agent (CMA), generative AI infrastructure layer enabling stateful, context-aware systems. It provides persistent memory across episodic, semantic, and procedural layers, supporting multi-agent coordination, retrieval, and lifecycle management. CMA addresses LLM statelessness and enables production-grade personalization and long-term context in AI applications.
-
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.
-
Meta Reports 4x Higher Bug Detection with Just-in-Time Testing
Meta introduces Just-in-Time (JiT) testing, a dynamic approach that generates tests during code review instead of relying on static test suites. The system improves bug detection by ~4x in AI-assisted development using LLMs, mutation testing, and intent-aware workflows like Dodgy Diff. It reflects a shift toward change-aware, AI-driven software testing in agentic development environments.
-
CNCF Warns Kubernetes Alone Is Not Enough to Secure LLM Workloads
A new blog from the Cloud Native Computing Foundation highlights a critical gap in how organizations are deploying large language models (LLMs) on Kubernetes: while Kubernetes excels at orchestrating and isolating workloads, it does not inherently understand or control the behavior of AI systems, creating a fundamentally different and more complex threat model.
-
Anthropic Introduces Agent-Based Code Review for Claude Code
Anthropic has introduced a new Code Review feature for Claude Code, adding an agent-based pull request review system that analyzes code changes using multiple AI reviewers.