Skip to main content
← All Tags

AI Agents

112 articles in this category (Page 3 of 5)

AI NewsAI AgentsLanguage Model

Zhipu AI Releases GLM-4.7-Flash: A 30B-A3B MoE Model for Efficient Local Coding and Agents

Zhipu AI released GLM-4.7-Flash, a 31B parameter Mixture of Experts model achieving leading performance among 30B models on coding and reasoning benchmarks.

Read more
AI NewsAI AgentsDeveloper Tools

Vercel Releases Agent Skills: A Package Manager For AI Coding Agents

Vercel releases Agent Skills, a package manager for AI coding agents, with initial skills based on 10 years of React and Next.js optimization rules.

Read more
AI NewsAI AgentsLlamaIndex

How to Build a Self-Evaluating Agentic AI System with LlamaIndex and OpenAI

This tutorial details building an agentic AI workflow achieving reliable retrieval-augmented generation (RAG) with self-evaluation.

Read more
AI NewsAI AgentsHealthcare

How to Build a Safe, Autonomous Prior Authorization Agent for Healthcare Revenue Cycle Management with Human-in-the-Loop Controls

This tutorial demonstrates building an autonomous AI agent for healthcare prior authorization, achieving a 95% confidence level in approvals while incorporating human oversight.

Read more
AI NewsAI AgentsAgentic AI

Anthropic Releases Cowork As Claude’s Local File System Agent For Everyday Work

Anthropic’s Cowork enables agentic workflows on local files for non-coding tasks, currently in research preview for Claude Max subscribers.

Read more
AI NewsAI AgentsArtificial Intelligence

How This Agentic Memory Research Unifies Long Term and Short Term Memory for LLM Agents

Agentic Memory (AgeMem) achieves a 21.7% performance improvement on SciWorld by unifying long-term and short-term memory management within a single LLM policy.

Read more
AI NewsAI AgentsArtificial Intelligence

Google AI Releases Universal Commerce Protocol (UCP): An Open-Source Standard for Agentic Commerce

Google AI launched the Universal Commerce Protocol (UCP), an open-source standard aiming to streamline agentic commerce and reduce integration bottlenecks.

Read more
AI NewsAI AgentsOpen Source

SETA: Open Source Reinforcement Learning Environments for Terminal Agents

SETA introduces a new open-source toolkit and environment stack achieving state-of-the-art results on Terminal Bench, with 46.5% accuracy on version 2.0.

Read more
AI NewsEcommerceAI Agents

Every ecommerce hero needs a Sidekick

Shopify launched Sidekick, an AI assistant leveraging commerce knowledge and advanced reasoning to evolve their product taxonomy at scale.

Read more
AI NewsAI AgentsLangGraph

How to Design an Agentic AI Architecture with LangGraph and OpenAI Using Adaptive Deliberation, Memory Graphs, and Reflexion Loops

This tutorial details building an advanced Agentic AI system using LangGraph and OpenAI, achieving a 6-tool call limit for optimized performance.

Read more
AI NewsAI AgentsSoftware Engineering

AI Agents: Mastering 3 Essential Patterns (ReAct)

The ReAct pattern enables AI agents to reason and act iteratively, overcoming limitations of single-step responses and reducing hallucinations.

Read more
AI NewsAI AgentsAgentic AI

A Coding Guide to Design and Orchestrate Advanced ReAct-Based Multi-Agent Workflows with AgentScope and OpenAI

This tutorial demonstrates building a multi-agent incident response system using AgentScope, achieving complex workflows in pure Python.

Read more
AI NewsAI AgentsLanguage Model

Recursive Language Models (RLMs): From MIT’s Blueprint to Prime Intellect’s RLMEnv for Long Horizon LLM Agents

Recursive Language Models (RLMs) achieve up to 62% accuracy on CodeQA, significantly improving upon standard LLM performance and reducing query costs.

Read more
AI NewsAI AgentsLangGraph

How to Design Transactional Agentic AI Systems with LangGraph Using Two-Phase Commit, Human Interrupts, and Safe Rollbacks

This tutorial demonstrates building agentic AI systems with LangGraph, achieving transactional workflows with a 99.9% success rate in controlled environments.

Read more
AI NewsAI AgentsAgentic AI

Alibaba Tongyi Lab Releases MAI-UI: A Foundation GUI Agent Family that Surpasses Gemini 2.5 Pro, Seed1.8 and UI-Tars-2 on AndroidWorld

Alibaba’s MAI-UI achieves 76.7% success on the AndroidWorld benchmark, outperforming Gemini 2.5 Pro, Seed1.8, and UI-Tars-2 in mobile GUI navigation.

Read more
AI NewsAI AgentsOpen Source

NVIDIA Releases NitroGen: An Open Vision Action Foundation Model For Gaming Agents

NVIDIA released NitroGen, a foundation model trained on 40,000 hours of gameplay across 1,000+ games, enabling generalist gaming agents.

Read more
AI NewsAI AgentsAI Tool

MiniMax Releases M2.1: An Enhanced M2 Version with Features like Multi-Coding Language Support, API Integration, and Improved Tools for Structured Coding

MiniMax Releases M2.1, achieving 72.5% on SWE-Multilingual, outperforming Claude Sonnet 4.5 and Gemini 3 Pro across multiple programming languages.

Read more
AI NewsnpmAI Agents

MyceliuMail & MCP: New npm Packages for AI Agent Communication

Two new npm packages, MyceliuMail and MCP, aim to simplify cross-platform AI agent workflows with over 1700 combined downloads.

Read more
AI NewsAI AgentsMachine Learning

Stanford & Harvard Paper Decodes Agentic AI's Demo-vs-Reality Gap

A new paper from Stanford, Harvard, UC Berkeley, and Caltech proposes a unified framework for understanding adaptation in Agentic AI systems, explaining why they often excel in demos but struggle in real-world applications.

Read more
AI NewsAI AgentsAgentic AI

A Coding Guide to Build an Autonomous Multi-Agent Logistics System with Route Planning, Dynamic Auctions, and Real-Time Visualization Using Graph-Based Simulation

Build an Autonomous Multi-Agent Logistics System with route planning, dynamic auctions, and real-time visualization, achieving a simulation with 30 nodes and 5 agents.

Read more
AI NewsAI AgentsArtificial Intelligence

Google Introduces A2UI (Agent-to-User Interface): An Open Source Protocol for Agent Driven Interfaces

Google released A2UI, an open-source protocol enabling AI agents to define rich UIs as declarative JSON, improving agent interaction efficiency.

Read more
AI NewsAI AgentsAgentic AI

How to Build a Fully Autonomous Local Fleet-Maintenance Analysis Agent Using SmolAgents and Qwen Model

Build a fleet maintenance agent with SmolAgents and Qwen, achieving fully autonomous analysis and visualization without external API calls.

Read more
AI NewsLarge Language ModelAI Agents

NVIDIA Releases Nemotron 3: A Hybrid Mamba Transformer MoE Stack for Long Context Agentic AI

NVIDIA released the Nemotron 3 family of open models, with the Nano variant achieving 4x higher token throughput than Nemotron 2 Nano.

Read more
AI NewsTechnical WritingAI Agents

How to Document AI Agents (Because Traditional Docs Won't Cut It)

AI agent documentation requires a new framework to address non-deterministic behavior and complex failure modes.

Read more