{"slug": "axion-1-0-open-agent-foundation-models-simplified", "title": "Axion 1.0: Open Agent Foundation Models, Simplified", "summary": "Axion 1.0, a fully open agent foundation model, was released with a training recipe of only three stages: two lightweight supervised fine-tuning stages followed by reinforcement learning, with no dedicated midtraining stage. The release claims strong and broad agentic capabilities from that simplified pipeline.", "body_md": "We introduce Axion 1.0, a fully open agent foundation model that combines strong and broad agentic capabilities with a remarkably simple training recipe. Axion 1.0 is trained in only three stages: two lightweight supervised fine-tuning stages followed by reinforcement learning, without dedicated mid", "url": "https://wpnews.pro/news/axion-1-0-open-agent-foundation-models-simplified", "canonical_source": "https://aiflash.com/news/145241/", "published_at": "2026-11-04 05:04:47+00:00", "updated_at": "2026-11-04 05:19:39.743927+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "large-language-models", "ai-research"], "entities": ["Axion 1.0"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/axion-1-0-open-agent-foundation-models-simplified", "markdown": "https://wpnews.pro/news/axion-1-0-open-agent-foundation-models-simplified.md", "text": "https://wpnews.pro/news/axion-1-0-open-agent-foundation-models-simplified.txt", "jsonld": "https://wpnews.pro/news/axion-1-0-open-agent-foundation-models-simplified.jsonld"}}