AI Briefing
KO

XYZ AI Lab Unveils XYZ-Aquila-mini, a Model for Agents

·2026.07.27 21:00

Key point

XYZ AI Lab has released XYZ-Aquila-mini, a deep search agent model based on Qwen3.6.

Details

XYZ-Aquila, developed by XYZ AI Lab, is an open-weight Deep Search agent product family. The newly released XYZ-Aquila-mini is a model post-trained via the AI4AI pipeline based on Qwen3.6-35B-A3B.

Key features are as follows:

  • Agent Optimization: Optimized for long-horizon planning, English and Chinese web browsing, multi-source evidence gathering, source verification, and recovery from environment interaction failures.
  • Reasoning and Tool Use: A Thinking Model that supports Qwen-compatible reasoning and tool-call formats.
  • AxisAgentic Harness: Along with the model's own performance, an open-source harness is provided that includes search, scraping, Python tool implementation, and benchmark evaluation workflows.

Additionally, the higher-tier XYZ-Aquila-pro model with 397B parameters is also available.

qwenreasoning-modelai-agentsopen-weightsdeep-searchxyzai-lab
Read originalShare on Threads

This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.

Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.

Related

TLDR AIQwen Intelligence Launches Three Mobile AI Agents and Open Benchmark SuiteGoogle Cloud AIGoogle Cloud outlines three key AI stack priorities for startupsHacker NewsApple Releases LensVLM-9B for Processing Compressed Text ImagesOpenAI BlogRingg Automates 65% of Customer Inquiries with AI Agent Based on OpenAI GPT-5.6GitHub BlogGitHub-Yale Survey: 80% of Developers Want Energy-Efficient Code Tools, but Action Remains MinimalOpenAI BlogOpenAI Launches GPT-6 Sol and Luna… API Prices Cut by 50% Compared to GPT-5.6