Skip to main content
← All Tags

AI Agents

112 articles in this category (Page 4 of 5)

AI NewsAI AgentsAgentic AI

How to Orchestrate a Fully Autonomous Multi-Agent Research and Writing Pipeline Using CrewAI and Gemini

Implement a two-agent CrewAI system with Gemini Flash to automate research and writing, demonstrating a practical agentic workflow.

Read more
AI NewsAI AgentsOpen Source

CUGA on Hugging Face: Democratizing Configurable AI Agents

IBM Research's CUGA, an open-source AI agent, achieved #1 ranking on AppWorld with 750 real-world tasks, and is now available on Hugging Face.

Read more
AI NewsAI AgentsAgentic AI

How to Design a Gemini-Powered Self-Correcting Multi-Agent AI System with Semantic Routing, Symbolic Guardrails, and Reflexive Orchestration

This tutorial details a system designed with Gemini achieving self-correction through semantic routing, symbolic guardrails, and iterative refinement loops.

Read more
AI NewsSoftware DevelopmentAI Agents

How Stack Overflow’s MCP Server is helping HP modernize the software development lifecycle

HP is leveraging Stack Overflow’s Model Context Protocol (MCP) server to improve developer productivity and break down knowledge silos within a 4,000+ developer organization.

Read more
AI NewsAI AgentsTutorials

How to Design a Fully Local Agentic Storytelling Pipeline Using Griptape Workflows, Hugging Face Models, and Modular Creative Task Orchestration

This tutorial demonstrates building a fully local agentic storytelling system, generating a coherent short story without relying on external APIs.

Read more
AI NewsReinforcement LearningAI Agents

Agent Lightning adds RL to AI agents without code rewrites

Agent Lightning enables reinforcement learning for AI agents, improving performance on complex tasks by up to 20% with minimal code changes.

Read more
AI NewsMachine LearningAI Agents

Codex Now Automates End-to-End Machine Learning Experiments

OpenAI’s Codex can now automate full ML experiments, including data validation, training, evaluation, and model conversion, reducing engineering overhead.

Read more
AI NewsAI AgentsAI Tool

CopilotKit v1.50 Leverages AG-UI for Streamlined In-App Agent Integration

CopilotKit v1.50 introduces the useAgent hook, simplifying the integration of agentic AI into applications via the AG-UI protocol.

Read more
AI NewsAI AgentsMachine Learning

OpenAI Introduces GPT-5.2: A Long Context Workhorse For Agents, Coding And Knowledge Work

OpenAI’s GPT-5.2 achieves state-of-the-art performance on long-context tasks, exceeding industry professionals on 70.9% of knowledge work comparisons.

Read more
AI NewsAI AgentsProcedural Learning

A Coding Guide to Build a Procedural Memory Agent That Learns, Stores, Retrieves, and Reuses Skills as Neural Modules Over Time

This tutorial details building an AI agent with procedural memory, demonstrating a 10x improvement in task completion efficiency through skill reuse.

Read more
AI NewsSoftware DevelopmentAI Agents

Kiro Powers Launch at AWS re:Invent 2025: Specialized AI for Development

AWS re:Invent 2025 introduces Kiro Powers, a new agentic IDE feature that integrates specialized tools from ISVs like Stripe and Netlify.

Read more
AI NewsAgentic AIAI Agents

How to Build an Adaptive Meta-Reasoning Agent That Dynamically Chooses Between Fast, Deep, and Tool-Based Thinking Strategies

Adaptive agents choose between fast, deep, and tool-based reasoning with 85% accuracy in query classification.

Read more
AI NewsAgentic AIAI Agents

Lux Surpasses Google Gemini CUA with 83.6% Accuracy on Online Mind2Web Benchmark

Lux, a new foundation computer use model by OpenAGI, achieves 83.6% accuracy on Online Mind2Web, outperforming Google Gemini CUA and others.

Read more
AI NewsAI AgentsBeginners Guide

Beyond Chatbots: My First Steps into the World of AI Agents

A beginner's journey reveals AI agents' potential beyond chatbots through Kaggle's intensive program.

Read more
AI NewsAI AgentsEducation

AI Agents Intensive: A Valuable Learning Experience

Sameer Sam highlights core AI agent concepts learned from the AI Agents Intensive program in 2025.

Read more
AI NewsAI AgentsResearch Tools

ScholarMindAI: Building Multi-Agent Academic Research Assistants with Google's AI Agents Intensive

ScholarMindAI, a multi-agent academic research assistant, automates paper summarization and literature review using Google's AI Agents Intensive.

Read more
AI NewsAgentic AIAI Agents

Google DeepMind Researchers Introduce Evo-Memory Benchmark and ReMem Framework for Experience Reuse in LLM Agents

Google DeepMind's Evo-Memory benchmark boosts LLM agent performance with 0.65 exact match accuracy on Gemini 2.5 Flash.

Read more
AI NewsMobile DevelopmentAI Agents

First Native Mobile AI Agent Open-Sourced

The first native mobile AI agent has been released as open-source, enabling on-device AI processing without cloud dependency.

Read more
AI NewsAI AgentsMachine Learning

Microsoft AI Releases Fara-7B: An Efficient Agentic Model for Computer Use

Microsoft’s Fara-7B, a 7 billion parameter agentic model, achieves 73.5% success on the WebVoyager benchmark, offering a cost-effective alternative to larger systems.

Read more
AI NewsAI AgentsArtificial Intelligence

How to Build a Neuro-Symbolic Hybrid Agent that Combines Logical Planning with Neural Perception for Robust Autonomous Decision-Making

This tutorial demonstrates building a neuro-symbolic agent, achieving a seamless integration of symbolic reasoning and neural learning for robust autonomous decision-making.

Read more
AI NewsAgentic AIAI Agents

Designing a Multi-Agent RL System for Grid Navigation

A multi-agent RL system navigates an 8x8 grid with obstacles, achieving goal-reaching through Q-learning and adaptive coordination.

Read more
AI NewsAI AgentsEditors Pick

Google Antigravity Makes the IDE a Control Plane for Agentic Coding

Google launched Antigravity on November 18, 2025, an agentic IDE built on VS Code and Gemini 3 Pro, aiming for autonomous software task execution.

Read more
AI NewsAgentic AIAI Agents

OpenAI Debuts GPT-5.1-Codex-Max, a Long-Horizon Agentic Coding Model With Compaction for Multi-Window Workflows

OpenAI's GPT-5.1-Codex-Max achieves 77.9% accuracy on SWE-bench Verified with compaction, enabling 24-hour autonomous coding sessions.

Read more
AI NewsAI AgentsDevOps

How to Accelerate AI Agent Deployment: A Step-by-Step Guide

AI agents represent a fundamental shift in enterprise automation, but only 11% of organizations have achieved full deployment.

Read more