DeepReinforce Releases Ornith-1.0: An Open-Source Coding Model Family That Learns Its Own RL Scaffolds

DeepReinforce has released Ornith-1.0 , an open-source model family built for agentic coding. The lineup spans four sizes, from a 9B dense model to a 397B mixture-of-experts flagship. Every checkpoint ships under the MIT license on Hugging Face. The models are post-trained on top of pretrained Gemma 4 and Qwen 3.5.

Most coding agents pair a model with a fixed, human-designed harness. Ornith-1.0 instead learns to write its own. The DeepReinforce research team reports state-of-the-art results among open models of comparable size.

Ornith-1.0 is a set of reasoning models tuned for coding agents. The variants are 9B Dense, 31B Dense, 35B MoE, and 397B MoE. The 35B model is mixture-of-experts and activates roughly 3B parameters per token. FP8 and GGUF builds are also published for faster local serving.

Each model is a reasoning model. Replies open with a block before the final answer. The serving recipes enable a reasoning parser, so that trace returns in a separate reasoning_content field. The models also emit well-formed tool calls for agent loops.

Deployment is straightforward. The 9B model is about 19GB in bf16 and serves on a single 80GB GPU. Serving recipes target vLLM, SGLang, and Transformers. Each model exposes an OpenAI-compatible endpoint. Standard agent frameworks therefore work without code changes.

Most coding agents rely on a scaffold, also called a harness . A scaffold wraps the model with memory, tools, error handling, and orchestration logic. AI teams usually hand-design one scaffold per task category.

Ornith-1.0 treats the scaffold as a learnable object instead. During reinforcement learning, the scaffold co-evolves with the model’s policy. Each RL step runs in two stages .

First , the model reads the task and its previous scaffold. It then proposes a refined scaffold. Second , it uses that scaffold and the task to generate a solution rollout. Reward from the rollout flows back to both stages.

So the model is optimized to author orchestration, not just answers. Over training, higher-reward scaffolds are mutated and selected automatically. Per-task strategies emerge without hand-engineered harness design.

Training also runs asynchronously, using a pipeline-RL setup. A staleness weight downweights older, off-policy tokens and drops them past a threshold. The optimization uses a token-level GRPO objective.

Letting a model write its own scaffold invites reward hacking. A scaffold could read visible test files and hardcode expected outputs. It could also copy an oracle solution sitting in the environment. DeepReinforce team describes three defense layers.