HOT RADAR
llmHEAT 7.4°

AI CURATED HOT STORY · 11/17/2026

ByteDance and Duke Unveil Axion 1.0 with Two-Stage Agent Training

1 reports archived1 independent sourcesupdated 11/17/2026, 11:38:00
Synthesis & Latest Updates
1 Sources Cross-Validated

A team from Duke University, ByteDance, the University of Maryland and SUNY Buffalo released Axion 1.0, which reduces agent training to two stages: supervised fine-tuning and reinforcement learning, dropping mid-training, DPO and on-policy distillation. Axion 1.0-122B scores 59.0% on the restricted-access Humanity's Last Exam, above GPT-6, while the 35B variant reaches 62.2% on SEAL-0. The team open-sourced data construction, filtering, verification, prompts and training code.

LATEST/A team from Duke University, ByteDance, the University of Maryland and SUNY Buffalo released Axion 1.0, which reduces agent training to two stages: supervised fine-tuning and reinforcement learning, dropping mid-training, DPO and on-policy distillation. Axion 1.0-122B scores 59.0% on the restricted-access Humanity's Last Exam, above GPT-6, while the 35B variant reaches 62.2% on SEAL-0. The team open-sourced data construction, filtering, verification, prompts and training code.

Hourly heat curve

11 fully observed hours
Now
7.4
Peak
9.422:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first