Storia in 2 fonti

Orchard: An open framework for scalable agentic AI

Orchard is an open-source framework for the research community to train and evaluate AI agents across task types. It reduces complexity while supporting strong performance from smaller models by enabling researchers to reuse the same infrastructure:

Raccontata da

microsoft.com

aibusiness.com

Confronto fonti

2 prospettive sulla stessa storia

AI · summaries

microsoft.comStai leggendo17 g fa

Orchard: An open framework for scalable agentic AI

Microsoft open-sourced Orchard, an agentic AI framework; Orchard-SWE achieves 69.7% on SWE-bench with 3B parameters, matching systems 10x larger. Trains agents directly in real deployment harnesses (Claude Code, Codex, OpenClaw) rather than simplified stand-ins, eliminating training-deployment gap and reducing infrastructure lock-in.

originale

aibusiness.com16 g fa

Microsoft Framework to Cut AI Agent Training Costs

Microsoft releases framework to reduce the cost of training AI agents.

Leggi questa versione → originale

Timeline cronologica

lunedì 3 agosto 2026·microsoft.com
Orchard: An open framework for scalable agentic AI
Orchard is an open-source framework for the research community to train and evaluate AI agents across task types. It reduces complexity while supporting strong performance from…
martedì 4 agosto 2026·aibusiness.com
Microsoft Framework to Cut AI Agent Training Costs
Microsoft releases framework to reduce the cost of training AI agents.