Microsoft Open-Sources Orchard: A Framework for Training and Evaluating AI Agents
adnan_hashmi · x · 2026-08-05
Microsoft Research has officially open-sourced the Orchard framework, designed to help the research community train and evaluate AI agents across various task types.
By enabling researchers to reuse the same infrastructure, the framework reduces development complexity while supporting strong performance from smaller models.
More from coding & agent
- Agent Search Workflow for Obsidian: Semantic Meets Keyword — dSebastien · 2026-08-05
- NeurIPS 2026 Call for Papers: Focus on Responsible Meta-Agents — RobertTLange · 2026-08-05
- Spring Evals: Benchmarking LLMs on Real-World Spring Boot 4 Code with Hidden Tests — therealdanvega · 2026-08-05
- Navigating SAP's Agent Architecture: MCP for Tool Execution, A2A for Orchestration — SillyDot3305 · 2026-08-05
- YC's Multiplayer Agent Harness: Great Decoupled Architecture, But It Kills KV Cache — Instance_Not_Found · 2026-08-05
- The 'oh-my' Configuration Trend in Open-Source Coding Agents — HarveenChadha · 2026-08-05