Research Engineer
Atul Saxena
I build the environments models are trained in, and the tools that show what they learned.
- RL Systems
- Interpretability
- ML Infrastructure
Research Engineer
Atul Saxena
I build the environments models are trained in, and the tools that show what they learned.
Atul Saxena, Divyanshi Sharma
In plain terms
Most systems ask a language model to make a decision and then parse whatever sentence comes back. Noma skips the sentence. It answers with numbers you can threshold on, in about 16 milliseconds, and it can say "none of these" instead of guessing.
Noma is an open decision model. Given a state — a ticket, a log line, an agent’s last step, a contract clause — and a few typed questions, it returns a calibrated probability for every option, a separate "none of these" signal, and a measure of its own uncertainty. It never writes text, so there is nothing to parse and nothing to wait for. The paper documents the architecture and ablates each component across 20 controlled training runs.