LinkKwaipilotTool
It offers an efficient alternative for self-hosted agentic coding workflows, keeping compute requirements low by activating only 3 billion parameters per inference step.
The release card outlines critical failure modes in agentic RL: naive binary reward structures caused training collapse by encouraging pathological behaviour like massive parallel tool calls. Addressing these through granular execution feedback and penalty signals proved essential for multi-epoch RL stability.
Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.
Similar in content, found by the AI search.
Link:ornith-ai
ornith-ai has released Ornith-1.5-397B, an open-source multimodal mixture-of-experts model under the MIT licence. With 397 billion parameters and an end-to-end self-improvement loop, it delivers coding and reasoning benchmark performance comparable to top proprietary models.
Link:Poolside
Poolside has released Laguna-S-2.1, a Mixture-of-Experts language model featuring 118B total parameters with approximately 8B activated parameters per token. Targeted at software engineering and long-horizon agentic workflows, the model is available under the permissive OpenMDW-1.1 license.
Article:Luis Chavez-Mattos
Deep Reinforce has introduced Ornith 1.5 35B-A3B, a mixture-of-experts model activating roughly 3 billion parameters per token out of 35 billion. According to published benchmarks, it surpasses direct competitors like Qwen3.6-35B across coding and agentic tasks, while closing the gap on much larger models such as Qwen3.5-397B.
Link:Xiaomi MiMo Team
Xiaomi has unveiled MiMo-V2.5-Pro, an open-source Mixture-of-Experts model featuring 1.02 trillion total parameters with 42 billion active. The model supports a 1M-token context window and is specifically designed for complex agentic workflows and long-horizon software engineering.
Link:Moonshot AI
Moonshot AI has released Kimi K3, an open-weight native multimodal agentic model featuring 2.8 trillion total parameters and a 1-million-token context window. The architecture uses a sparse MoE setup that activates 104 billion parameters per token.
Link:deep-reinforce.com
Ornith-1.0 is an open-source model family tailored for agentic coding, spanning parameter sizes from 9B to 397B. Built on Gemma 4 and Qwen 3.5, the architecture trains models to jointly generate both code solutions and the task-specific scaffolds directing them.
Parts of this content were created with the assistance of AI.
