M

GELab-Zero-4B-preview-Sico-Evolution

Multimodalpor Microsoft·Página del modelo

Modelo multimodal de 4B parámetros de Microsoft del laboratorio GELab para la comprensión imagen-texto con generalización en cero ejemplos.

Share:

Modelo base

GELab-Zero-4B-preview

Descripción del Modelo

  • 🔧 This model is part of Sico — an open-source platform for building and evolving Digital Workers, where AI agents and their human operators co-evolve through real work.
  • Star the Sico repository to follow new evolved models and our model evolution pipeline — this GUI agent is the first public release, with more on the way.
  • 📄 Backed by our survey on agentic evolution and co-evolving human–AI systems.

GELab-Zero-4B-preview-Sico-Evolution

A 4B GUI agent fine-tuned (LoRA) from the open-source GELab-Zero-4B-preview base model on Microsoft Edge and Copilot UI trajectories. It is built with our general-purpose GUI model evolution pipeline — an iterative mechanism that keeps lifting an agent's real task success rate round after round, and transfers to any GUI app.

Highlights

From 39.8% to 82.9%: Sico-Evolution achieves a dominant 82.9% Task Success Rate, a massive +43.1% absolute surge over the 39.8% base-model baseline.

Outperforms Closed-Source SOTAs: It edges out top proprietary giants like gpt-5.4 (79.7%), Claude-Opus-4.6 (81.3%), and claude-opus-4.7 (82.1%).

Vastly Exceeds Open-Source Models: It crushes leading competitors including kimi-k2.6 (62.6%) and UI-Venus-1.5-30B (61.0%).

Results

Edge / Copilot Test Cases — TSR

Autor
M
Microsoft
Organización · ✓
microsoft
Detalles
Descargas489
Me gusta45
AccesoCódigo Abierto
Tareaimage-text-to-text
Parámetros4.4B
Tendencia44
Licenciaapache-2.0
Libreríatransformers
Creado30 jun 2026
Actualizado4 jul 2026
Ver en Hugging Face
Idiomas
enzh
Entiende todo el contexto.

Regístrate para leer casos de estudio completos, acceder a métricas detalladas y recibir todos los reportes.