Axion 1.0: ByteDance-Backed Open Agent Foundation Model With 3-Stage Recipe
Yuqi Jia · hf · 2026-11-04
Axion 1.0 is a fully open agent foundation model from ByteDance, Duke, Maryland and Buffalo, trained with a remarkably simple three-stage recipe: two lightweight SFT stages plus reinforcement learning — no mid-training, DPO, or on-policy distillation. Stage one builds self-contained reasoning via model-aware data synthesis; stage two extends to tool-dependent reasoning with automatically verifiable tasks. Data and training recipe are fully released, with competitive agentic performance.
More from coding & agent
- With: an MIT-licensed systems language repo with 4,200+ commits and agentic dev workflow built in — QuixiAI · 2026-11-04
- GitHub team shares ~30 min of Copilot demos, from editor to Slack workflows — lee_stott · 2026-11-04
- Microsoft's WebHarbor docks 153 real websites into dockerized environments for GUI agent RL — microsoft · 2026-11-04
- ToolSpace mines real MCP execution traces to synthesize tool environments for long-horizon agents — RUC · 2026-11-04
- Turn count misleads agent benchmarks: DEPTH measures sequential dependency depth instead — Yu Jiang · 2026-11-04
- Karpathy builds HackerTube in ~2 hours with zero code using Opus 5.5 — FinanceYF5 · 2026-11-04