Orchard introduces an open-source agentic modeling framework with reusable environment primitives and domain-specific training recipes that deliver state-of-the-art open-source results on coding, web navigation, and assistant benchmarks.
We embed each task intent with Qwen/Qwen3-Embedding-8B and greed- ily remove tasks whose cosine similarity to a previously kept task exceeds 0.99 (-124,454, 88.9%→15,601)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Orchard: An Open-Source Agentic Modeling Framework
Orchard introduces an open-source agentic modeling framework with reusable environment primitives and domain-specific training recipes that deliver state-of-the-art open-source results on coding, web navigation, and assistant benchmarks.