Quanta AI Labs

Microsoft Research · Agent Framework

SkillOpt

Microsoft Research trainer that optimizes a markdown skill file like model parameters (epochs, mini-batches, validation gates) while the LLM stays frozen, producing a 300-2,000 token best_skill.md with no extra inference calls at deploy. Reports +23.5 points on GPT-5.5 in direct chat and best or tied-best on all 52 evaluated cells; MIT, ~15k stars.

Open the source ↗

Similar Agents & Automation releases

  • StreamVibe

    Chengzhi Liu, Yuxiang Lai and co-authors (arXiv:2610.34662) · Proactive video agent · Week 45, 2026

  • AutoSwarm

    HKUDS (Zhonghang Li, Zongwei Li, Chao Huang) · Agent swarm orchestrator · Week 45, 2026

  • Lightpanda Browser

    lightpanda-io · Headless agent browser · Week 45, 2026

  • Scenario Agent Skills

    Scenario (scenario-labs) · Creative agent skills · Week 45, 2026

  • SkyRL

    NovaSky-AI (Berkeley Sky Computing Lab, with Anyscale) · RL training library · Week 45, 2026

  • DeskcommCRM

    melgarafael · Self-hosted AI CRM · Week 45, 2026

More from Microsoft Research

  • Spatia

    Microsoft Research · Text-to-Video · Week 52, 2025

  • Fara-7B

    Microsoft Research · Desktop Agents · Week 49, 2025

Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.