Skip to main content
← All Tags

Agentic AI

195 articles in this category (Page 3 of 9)

AI NewsAgentic AIAI Infrastructure

Advanced Web Scraping with Crawl4AI: Markdown Generation, JS Execution, and Structured LLM Extraction

Learn to implement Crawl4AI v0.8.x for advanced web crawling, featuring JavaScript execution and LLM-based structured data extraction from unstructured HTML.

Read more
AI NewsAgentic AIAI Agents

Google Skills in Chrome: Native Browser-Level Prompt Templating for AI Workflows

Google launches 'Skills' in Chrome on April 14, 2026, enabling users to save reusable AI prompts as one-click browser workflows for multi-tab execution.

Read more
AI NewsAgentic AIAI Agents

Building Multi-Agent Data Analysis Pipelines with Google ADK

Learn to build a modular multi-agent system using Google ADK to automate data ingestion, statistical modeling, and visualization in Python. This tutorial demonstrates orchestrating five specialized agents to perform Shapiro-Wilk tests and ANOVA, significantly reducing manual analysis time in production-grade pipelines.

Read more
AI NewsAgentic AIAI Agents

Google Research Unveils Vantage: Scaling Durable Skills Assessment via Executive LLMs

Google’s Vantage protocol achieves a 0.88 Pearson correlation with human experts in scoring creativity using a novel Executive LLM architecture.

Read more
AI NewsAgentic AILarge Language Model

MiniMax M2.7: Open-Source Self-Evolving Model Matches GPT-5.3-Codex on SWE-Pro

MiniMax open-sources M2.7, a self-evolving MoE model achieving 56.22% on SWE-Pro and 57.0% on Terminal Bench 2, matching GPT-5.3-Codex in production-level software engineering.

Read more
AI NewsAgentic AIGenerative AI

How to Build a Secure Local-First Agent Runtime with OpenClaw

Learn to deploy a secure local-first agent runtime using OpenClaw Gateway and structured skills, enabling deterministic tool execution and model routing within a loopback-bound environment.

Read more
AI NewsArtificial IntelligenceAgentic AI

Meta Superintelligence Lab Unveils Muse Spark: Natively Multimodal Model with Thought Compression

Meta Superintelligence Lab releases Muse Spark, achieving a 72.2 score on ScreenSpot Pro through native multimodality and 10x compute efficiency over Llama 4 Maverick.

Read more
AI NewsAgentic AISoftware Engineering

Scaling Computer Use Agents: OSGym Framework Manages 1,000+ Replicas at $0.23/Day

OSGym enables training computer use agents by managing 1,000+ OS replicas at just $0.23 per day using hardware-aware orchestration and CoW disk management.

Read more
AI NewsAgentic AISoftware Engineering

Z.AI Releases GLM-5.1: 754B Open-Weight Agentic Model Sets New SWE-Bench Pro SOTA

Z.AI's GLM-5.1 achieves a state-of-the-art 58.4 on SWE-Bench Pro and sustains 8-hour autonomous execution for complex engineering tasks.

Read more
AI NewsAgentic AILanguage Model

Mastering Google LangExtract: A Technical Guide to Structured Document Intelligence

Automate document intelligence with Google LangExtract and OpenAI to transform unstructured text into grounded, machine-readable datasets with exact source spans.

Read more
AI NewsAgentic AIMachine Learning

Google AI Research Introduces PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing

Google AI Research debuts PaperOrchestra, a multi-agent system that transforms raw experimental logs into submission-ready LaTeX papers, achieving simulated acceptance rates of up to 84%.

Read more
AI NewsAgentic AISoftware Engineering

Advanced Agentic Workflows: Mastering Tool Combination and Context Circulation in Gemini API

Google's March 2026 Gemini API updates enable combining Google Search, Maps, and custom functions in a single call using context circulation and unique tool IDs.

Read more
AI NewsAgentic AITech News

How Creative AI Stacks are Transforming Global Fashion Design and Supply Chains

Over 45% of global apparel brands have integrated AI-driven design tools to reduce development lead times according to McKinsey’s 2026 State of Fashion report.

Read more
AI NewsAgentic AIOpen Source

AutoAgent: Automating AI Agent Optimization and Harness Engineering

AutoAgent autonomously optimizes agent harnesses, achieving a 96.5% score on SpreadsheetBench and a top GPT-5 score on TerminalBench within 24 hours.

Read more
AI NewsAgentic AIMachine Learning

Google DeepMind AlphaEvolve: LLM-Driven Evolutionary Search Outperforms Human-Designed Game Theory Algorithms

DeepMind's AlphaEvolve uses Gemini 2.5 Pro to evolve MARL source code, discovering algorithms that outperform expert-designed baselines in 10 of 11 test games.

Read more
AI NewsAgentic AILanguage Model

Building Production-Ready Agentic Systems with Z.AI GLM-5

Develop scalable agents with Z.AI GLM-5, utilizing a 744B parameter MoE architecture and native tool calling for production environments.

Read more
AI NewsAgentic AILarge Language Model

Arcee AI Releases Trinity Large Thinking: An Apache 2.0 Open Reasoning Model for Long-Horizon Agents

Arcee AI releases Trinity Large Thinking, a 400B sparse MoE reasoning model under Apache 2.0 with a 262,144-token context window.

Read more
AI NewsAgentic AIAI Infrastructure

Defeating the ‘Token Tax’: Google Gemma 4 and NVIDIA Revolutionize Local Agentic AI

NVIDIA RTX GPUs deliver up to 2.7x inference performance gains over M3 Ultra chips, enabling Google Gemma 4 models to run locally and eliminate astronomical cloud API Token Taxes.

Read more
AI NewsAgentic AITutorials

Deploying Gemma 3 1B: A Production-Ready Pipeline with Hugging Face Transformers

Build an efficient Gemma 3 1B Instruct pipeline on Colab using Hugging Face Transformers, bfloat16 precision, and automated chat templates for low-latency text generation.

Read more
AI NewsAgentic AIMachine Learning

Z.ai GLM-5V-Turbo: Native Multimodal Vision Model for Agentic Engineering

Zhipu AI (Z.ai) launches GLM-5V-Turbo, a native multimodal vision coding model featuring a 200K context window and optimized integration for OpenClaw agentic workflows.

Read more
AI NewsAgentic AIAI Agents

Building Production-Ready Agentic Workflows with AgentScope and ReAct Agents

Learn to build production-ready AgentScope workflows using ReAct agents, custom toolkits, and Pydantic for structured outputs. This tutorial demonstrates how to orchestrate multi-agent debates and concurrent analysis pipelines using OpenAI models to achieve high-fidelity reasoning and automated tool execution for enterprise-grade AI applications.

Read more
AI NewsAgentic AIAI Agents

How to Build and Evolve Custom OpenAI Agents Using the A-Evolve Framework

A-Evolve automates agent improvement through workspace mutations, achieving measurable gains in train and holdout scores via iterative benchmarking cycles.

Read more
AI NewsAgentic AIVoice AI

Salesforce AI Research Releases VoiceAgentRAG: A Dual-Agent Memory Router that Cuts Voice RAG Retrieval Latency by 316x

Salesforce AI Research released VoiceAgentRAG, an open-source architecture that reduces retrieval latency by 316x using a dual-agent system to meet the 200ms voice response budget.

Read more
AI NewsAgentic AISoftware Engineering

Chroma Releases Context-1: A 20B Agentic Search Model for Multi-Hop Retrieval and Context Management

Chroma's new 20B Context-1 model achieves 10x faster inference and 25x lower costs than GPT-5.4 by decoupling search from generation.

Read more