Axion 1.0 open foundation model delivers strong agent reasoning
Axion 1.0: Open Agent Foundation Models, Simplified
Artificial Intelligence
Summary
Building smart AI agents that solve complex problems usually requires complicated training. The authors present Axion 1.0, a new AI model trained by just three steps that teaches it how to think and use tools effectively. They generate tough problems for the AI to learn from and improve itself, then train it to use real-world data and tools. This simple method produces a powerful and open AI agent that performs well on many tests and can be freely shared and improved by others.
What this means in practice
- •For software developers: Build AI agents that reason and interact with tools using an open, reproducible training method.
- •For automation engineers: Create intelligent systems that perform complex, multi-step tasks based on real-world data and external tools.
Authors
Yuqi Jia, Yunjie Tian, Jiayu Zheng, Yijun Liang, Jingchen Sun, Mengyu Zhao, Di Fu
Abstract
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-training, direct preference optimization (DPO), or on-policy distillation (OPD). The first SFT stage develops strong self-contained reasoning through model-aware data construction, where we synthesize challenging problems and adversarially strengthen them based on the base model's own successful solution strategies. The second stage extends these capabilities to tool-dependent reasoning through a scalable pipeline for constructing diverse and automatically verifiable tasks grounded in real-world data sources and deterministic computation. Finally, reinforcement learning further strengthens long-horizon reasoning and interaction with external tools and environments. Despite this compact training recipe, Axion 1.0 achieves strong performance across a broad suite of agentic benchmarks and is competitive with leading commercial models on several of them. Equally importantly, Axion 1.0 is open beyond model weights: we release the complete recipe, including data construction, generation, filtering, verification, prompts, and training code, enabling the entire development process to be reproduced and extended. Axion 1.0 demonstrates that strong agent foundation models can be both open and simple, offering a practical and reproducible path toward advancing open agentic intelligence.