Making Science Programmable.

Dynamical Systems turns physical science into trainable experience. We make every experiment verifiable, replayable, and compounding.

Research

Can a Self-Driving-Lab Agent Tell When the Evidence Is Enough?

We turn the historical record of a lab into source-located replay tasks that measure evidence-boundary judgment before a self-driving lab is trusted to run on its own. Across six frontier models and 1,872 trajectories, agents reach a valid decision on 90% of runs and the reference-equivalent path on 72%, and no model clears the benchmark.

June 2026

Scaling Test-Time Verification for Novel Materials

Crystal diffusion models encode property signals in their hidden states that they never use during sampling. Probe-gradient guidance steers unconditional generation toward target properties at test time, comparable to conditional models at over 50x the speed.

April 2026

The Missing Layer in Autonomous Science

Multi-turn RL in verified campaign environments lifts hypothesis accuracy from 55.2% to 79.3% on held-out campaigns, surpassing GPT-5.4 with 3B active parameters.

April 2026