Skip to main content
← All Tags

Agentic AI

195 articles in this category (Page 2 of 9)

AI NewsAgentic AIMachine Learning

Meta Autodata: Agentic Framework for High-Quality Training Data Creation

Meta AI introduces Autodata, an agentic framework that enables autonomous data creation, increasing performance gaps between model solvers from 1.9% to 34%.

Read more
AI NewsAgentic AISoftware Engineering

Poolside AI Launches Laguna XS.2 and M.1: High-Performance Agentic Coding via MoE

Poolside AI releases Laguna XS.2 and M.1 models, achieving up to 72.5% on SWE-bench Verified using specialized Mixture-of-Experts architectures.

Read more
AI NewsAgentic AIMachine Learning

Optimizing Long-Term Memory Retrieval with Reinforcement Learning for LLM Agents

Build a PPO-trained RL agent that optimizes long-term memory retrieval for LLMs, outperforming standard cosine similarity in complex QA tasks.

Read more
AI NewsAgentic AIComputer Vision

Building VLA-Inspired Embodied Agents via Latent World Modeling and MPC

Learn to build a lightweight Vision-Language-Action agent using NumPy-rendered RGB observations and PyTorch to perform latent state prediction and real-time MPC planning.

Read more
AI NewsAgentic AILarge Language Model

Evaluating Agentic Reasoning: The 7 Benchmarks Defining Frontier LLM Performance

Frontier models now exceed 80% on SWE-bench Verified, yet reliability remains low with τ-bench pass^8 scores falling below 25% in retail domains.

Read more
AI NewsAgentic AILarge Language Model

How to Build a Fully Searchable AI Knowledge Base with OpenKB, OpenRouter, and Llama

Learn to build a local AI knowledge base using OpenKB and Llama 3.3, featuring automated wiki synthesis and programmatic graph analysis for structured information retrieval.

Read more
AI NewsVoice AIAgentic AI

Mastering the Deepgram Python SDK: A Full-Stack Voice AI Implementation Guide

Learn to implement a complete voice AI pipeline using the Deepgram Python SDK, featuring Nova-3 transcription, Aura-2 text-to-speech, and automated text intelligence.

Read more
AI NewsAgentic AISoftware Engineering

GitNexus: The Open-Source Knowledge Graph Engine for MCP-Native AI Coding

GitNexus indexes repositories into knowledge graphs, providing structural awareness to AI agents and gaining 28,000+ GitHub stars.

Read more
AI NewsAgentic AIAI Infrastructure

Google Cloud AI Research Unveils ReasoningBank: A Strategy-Distillation Framework for Agents

Google Cloud AI's ReasoningBank boosts agent success rates by 8.3% on WebArena by distilling reusable strategies from both successes and failures.

Read more
AI NewsAgentic AILarge Language Model

OpenAI GPT-5.5: First Fully Retrained Agentic Model Hits 82.7% on Terminal-Bench

OpenAI releases GPT-5.5, a fully retrained agentic model scoring 82.7% on Terminal-Bench 2.0 and 84.9% on GDPval for autonomous task execution.

Read more
AI NewsAgentic AIMachine Learning

Qwen3.6-27B: Dense 27B Model Outperforms 397B MoE in Agentic Coding

Alibaba releases Qwen3.6-27B, a dense model achieving 77.2 on SWE-bench Verified and outperforming the 397B MoE on repository-level reasoning.

Read more
AI NewsAgentic AITechnology

Designing Production-Grade Multi-Agent Systems with the CAMEL Framework

Design a production-grade multi-agent system with the CAMEL framework, achieving scores above 8.5/10 through structured planning, tool usage, and iterative critique loops.

Read more
AI NewsAgentic AISoftware Engineering

JiuwenClaw Unveils Coordination Engineering: Multi-Agent Synergy for 200-Page PPT Generation

JiuwenClaw's new Coordination Engineering enables autonomous agent teams to generate a 200-page technical presentation in under 20 minutes.

Read more
AI NewsAgentic AILarge Language Model

Xiaomi MiMo-V2.5-Pro: Frontier Agentic AI at 60% Lower Token Cost

Xiaomi releases MiMo-V2.5-Pro, matching GPT-5.4 benchmarks while reducing token costs by 60% for long-horizon agentic tasks.

Read more
AI NewsAgentic AIAI Infrastructure

Implementing Qwen 3.6-35B-A3B: Multimodal MoE with Thinking Control and Tool Calling

Deploy Qwen 3.6-35B-A3B, a 35B MoE model with 3B active parameters, featuring multimodal inference, thinking-budget control, and integrated tool calling for agentic AI workflows.

Read more
AI NewsSynthetic DataAgentic AI

Google Simula: A Reasoning-First Framework for Controllable Synthetic Data Generation

Google’s Simula framework generates specialized AI datasets across five domains, achieving 10% accuracy gains on GSM8k through automated complexity control.

Read more
AI NewsAgentic AIMachine Learning

Hugging Face Launches ml-intern: Automating LLM Post-Training Workflows

Hugging Face's ml-intern automates LLM post-training, boosting Qwen3-1.7B's GPQA score from 10% to 32% in under 10 hours.

Read more
AI NewsAgentic AIAI Infrastructure

Implementing Microsoft Phi-4-Mini: A Guide to Quantized Inference, RAG, and LoRA Fine-Tuning

Deploy Microsoft's 3.8B parameter Phi-4-mini-instruct with 4-bit quantization, 128K context window, and LoRA fine-tuning on consumer hardware.

Read more
AI NewsAgentic AILanguage Model

Moonshot AI Releases Kimi K2.6: Trillion-Parameter MoE for Long-Horizon Coding

Kimi K2.6 scales agent swarms to 300 sub-agents and 4,000 steps, achieving a leading 54.0 score on Humanity’s Last Exam (HLE-Full) with tools.

Read more
AI NewsAgentic AISoftware Engineering

Anthropic Releases Claude Opus 4.7: A Major Upgrade for Agentic Coding and High-Resolution Vision

Anthropic launches Claude Opus 4.7, featuring a 13% lift in coding benchmarks and 3x higher vision resolution to solve complex autonomous tasks.

Read more
AI NewsAgentic AILarge Language Model

Qwen3.6-35B-A3B: Sparse MoE Vision-Language Model with 3B Active Parameters

Alibaba releases Qwen3.6-35B-A3B, a sparse MoE model with 3B active parameters that outperforms larger models on Terminal-Bench 2.0 and SWE-bench.

Read more
AI NewsAgentic AIAI Infrastructure

Building Multi-Agent Systems with SmolAgents: Code Execution and Dynamic Orchestration

Learn to build production-ready multi-agent systems using SmolAgents v1.24.0, featuring Python-based code execution and dynamic tool management for complex reasoning tasks.

Read more
AI NewsAgentic AISoftware Engineering

Build Persistent AI Memory: A Guide to Mem0, OpenAI, and ChromaDB Integration

Learn to implement a universal long-term memory layer for AI agents using Mem0 and OpenAI to enable persistent, user-scoped conversational context and semantic search.

Read more
AI NewsAgentic AIAI Infrastructure

TinyFish AI Launches Unified Web Infrastructure for AI Agents

TinyFish AI launches a unified web infrastructure platform for AI agents, reducing token consumption by 87% and improving task completion rates by 2x.

Read more