Unverified50% confidenceFactExact time
Axion 1.0's training pipeline does not include dedicated mid-training, direct preference optimization (DPO) or on-policy distillation (OPD).
1
Sources
50%
Confidence
Long-term
Relevance
11/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAxion 1.0's training recipe has only three stages: two lightweight SFT stages and one reinforcement learning stage.71% similarUnverifiedThe approach with fine-tuning but without tool harness optimization, despite a larger training volume, achieved far less than AdaRSI.69% similarUnverifiedOffline RL trains a policy only on a pre-collected fixed dataset, with no further interaction with the environment during training, and its core advantage is that the training process is fully reproducible and auditable.68% similarUnverifiedThe core product Axonnic sells is training datasets, not the robot itself or a general-purpose foundation model.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1135494API
curl https://kongchang.com/api/v1/knowledge/claims/1135494MCP
get_claim(id=1135494)