Agentic AI

195 articles in this category (Page 7 of 9)

AI NewsLarge Language ModelAgentic AI

Alibaba Unveils Qwen3-Max-Thinking, a Trillion-Parameter Reasoning Model

Alibaba introduces Qwen3-Max-Thinking, a test-time scaled reasoning model with native tool use, achieving 92.8% accuracy on GPQA Diamond and 91.4% on LiveCodeBench v6.

Jan 28, 2026

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.

Jan 13, 2026

AI NewsAgentic AIEnterprise AI

Netomi’s lessons for scaling agentic systems into the enterprise

Netomi utilizes OpenAI’s GPT-4.1 and GPT-5.2 to achieve 98% intent classification accuracy while handling 40,000 concurrent customer requests per second.

Jan 8, 2026

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.

Jan 4, 2026

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.

Dec 30, 2025

AI NewsReinforcement LearningAgentic AI

Liquid AI’s LFM2-2.6B-Exp Tightens Small Model Behavior with Pure Reinforcement Learning

Liquid AI’s LFM2-2.6B-Exp surpasses DeepSeek R1-0528 on IFBench despite being 263x smaller, demonstrating efficient instruction following.

Dec 27, 2025

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.

Dec 24, 2025

AI NewsAgentic AIOpen Source

OpenAI, Anthropic, and Block Donate Agentic AI Projects to Linux Foundation

OpenAI and Anthropic donated AGENTS.md and Model Context Protocol to the Agentic AI Foundation (AAIF), signaling a push for open-source standards in the rapidly evolving agentic AI space.

Dec 23, 2025

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.

Dec 22, 2025

AI NewsAgentic AIArtificial Intelligence

Anthropic Releases Bloom: An Open-Source Framework for AI Behavioral Evaluation

Anthropic’s Bloom automates behavioral evaluations for frontier AI models, achieving up to 0.86 Spearman correlation with human labels.

Dec 21, 2025

AI NewsAgentic AITutorials

A Complete Workflow for Automated Prompt Optimization Using Gemini Flash, Few-Shot Selection, and Evolutionary Instruction Search

This tutorial demonstrates an automated prompt optimization workflow achieving improved sentiment analysis accuracy with Gemini 2.0 Flash.

Dec 19, 2025

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.

Dec 17, 2025

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.

Dec 15, 2025

AI NewsLLMsAgentic AI

Nemotron 3 Nano - A new Standard for Efficient, Open, and Intelligent Agentic Models

NVIDIA’s Nemotron 3 Nano 30B A3B model achieves up to 3.3x higher throughput than leading models while maintaining best-in-class reasoning accuracy.

Dec 15, 2025

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.

Dec 6, 2025

AI NewsMicroservicesAgentic AI

Treating Your Agents Like Microservices

Cisco’s Outshift explores multi-agent architectures as microservices, highlighting interoperability challenges in decentralized systems.

Dec 5, 2025

AI NewsAgentic AITutorials

How to Design a Fully Local Multi-Agent Orchestration System Using TinyLlama for Intelligent Task Decomposition and Autonomous Collaboration

Build a fully local multi-agent system using TinyLlama for task decomposition and autonomous collaboration, with 1.1B parameter efficiency.

Dec 5, 2025

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.

Dec 5, 2025

AI NewsAgentic AIMachine Learning

Meta-Cognitive AI Agent Learns to Balance Accuracy and Cost Across 600 Training Episodes

A meta-cognitive AI agent dynamically selects reasoning modes, achieving 92% accuracy on hard arithmetic tasks while minimizing computational cost.

Dec 3, 2025

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.

Dec 2, 2025

AI NewsAgentic AIMachine Learning

Master Agentic AI in 2026: A Step-by-Step Roadmap

Master agentic AI in 2026 with this step-by-step roadmap, as the global AI market surges toward mainstream adoption.

Dec 2, 2025

AI NewsAgentic AIMachine Learning

MiniMax-M2: Interleaved Thinking Redefines Agentic Coding Efficiency

MiniMax-M2 delivers 2x speed of leading models at 8% of their cost, revolutionizing agentic coding workflows.

Dec 1, 2025

AI NewsAgentic AILarge Language Model

DeepSeek Introduces DeepSeek-V3.2 and DeepSeek-V3.2-Speciale for Long-Context Reasoning and Agentic Workloads

DeepSeek’s new models cut long-context inference costs by 50% while matching GPT-5 and Gemini 3.0 Pro reasoning benchmarks.

Dec 1, 2025

AI NewsAgentic AIDistributed Systems

Matrix: A Ray Native Decentralized Framework for Multi Agent Synthetic Data Generation

Meta AI's Matrix framework boosts synthetic data generation by 2–15.4x in token throughput using decentralized peer-to-peer agents.

Nov 30, 2025