axion1_0
Frontier-level agent capabilities with nothing more than high-quality data and a simple training recipe: 2 SFT + RL, no mid-training/DPO/OPD. Full recipe released.
- llm
- agentic-ai
- agentic-workflow
- ai-agents
- multi-agent
- agent-skills
- agents
- ai
- Stars
- 44
- Forks
- 3
- + today
- +3
- Created
- 2d
Ranking data as of November 4, 2026 (UTC).
Star History
Today, hour by hour
03
Overview
Frontier-level agent capabilities with nothing more than high-quality data and a simple training recipe: 2 SFT + RL, no mid-training/DPO/OPD. Full recipe released. It ranks #172 on GitTiger, gaining +3 stars on November 4, 2026 (UTC).
The project is written in Python and has 3 forks. It was created 2d ago.
Installation
git clone https://github.com/bytedance/axion1_0.git
cd axion1_0
# see README for setup