Ultramarine 1 Flash: Scaling Non-Verifiable RL
Ultramarine 1 Flash: Scaling Non-Verifiable RL across Finance, Law, Consulting, and Operations
Paper Instruments
Ultramarine 1 Flash
Paper Instruments
An agentic model for professional knowledge work, post-trained from GLM-5.3 Flash with reinforcement learning on non-verifiable tasks. The announcement presents research results without a public model download or API release.
Specs
Model
- Family
- Ultramarine
- Variant
- 1 Flash
- Weights
- Proprietary
Dates
- Announced
- 14 Oct 2026
Articles
All articlespaperinstruments.com