Hey there, friend using a screen reader. I've carefully labeled every button and image on this site. Hope you have a smooth experience. If anything is inconvenient, my email is in the footer — just let me know and I'll fix it. — Store Owner
AI agents often fail because their instructions, or skills, are manually modified with no guarantee of improvement. Learn how SkillOpt turns skill editing into a training process, making agent behavior more reliable without changing model weights. The post SkillOpt: Agent skills as trainable parameters appeared first…
Microsoft Research
Eligibility
Check before you begin
Editorial note
What this means for you
Drafted by AI from the source above and published after human review. The official original remains authoritative.
What happened
微软研究院发布了 SkillOpt 方法，将 AI 代理的技能编辑从手动修改转变为训练过程，在不改变模型权重的情况下提高代理行为的可靠性。
Why it matters
对于正在学习 AI 代理开发的大学生，SkillOpt 提供了一种不依赖模型微调来优化代理行为的新思路。这意味着你可以通过调整技能参数来改进代理，而无需重新训练大型模型。
Today, we’re introducing two new models that bring advancements in near real-time reasoning to more effectively enable voice agents and make conversing with AI feel more intuitive and intelligent.
Google DeepMindPublished Sep 16, 2026
Official source · Google DeepMind BlogVerified Oct 13, 2026
Today, we’re announcing our new frontier model, Gemini 4 Argon, which is rolling out to a set of trusted cyber defenders through our Fairwind Program . Built to sustain deep reasoning across complex, long-horizon workflows, Argon is fundamentally changing the way we work and build at Google. It delivers frontier perfo…
Google DeepMindPublished Oct 1, 2026
Official source · Google DeepMind BlogVerified Oct 13, 2026
Building on the momentum of last week's Gemini 3.8 Live launch, today we are excited to introduce Gemini 3.8 Live with Live Avatar — bringing near real-time visual presence to our native live dialogue models. By pairing near real-time video generation with speech, the Live Avatar feature creates an experience that lis…
Google DeepMindPublished Sep 25, 2026
Official source · Google DeepMind BlogVerified Oct 13, 2026