Jarrod Barnes

I'm an ML researcher working on training and verification systems for open-ended scientific discovery.

I lead Dynamical Systems, an integrated materials lab that discovers, develops, and supplies materials for extreme environments.

Research threads
Scientific exploration SDL-2: Teaching AI to Explore the Physical World SDL-2 measures whether AI agents can decide, from experiments they choose, whether a magnet process will reliably meet a stated performance requirement. Frontier models show an emerging ability to establish what an unfamiliar physical system can reliably do. The findings implicate reasoning under variation as a central capability for scientific exploration. technical report code dataset campaign
Benchmark construction Latent Mining for Verifiable Scientific Task Generation A benchmark-construction method that turns disagreement between public scientific models into verifier-backed agent tasks. The first release is 165 regulatory-genomics triage tasks where 6 frontier agents reach an 11.3% aggregate strict solve rate and none exceed 15%. paper blog dataset
Verification Scaling Test-Time Verification for Novel Materials We studied how property estimates can guide crystal generation with Crystalite and MatterGen. With Crystalite's generator fixed, a trained probe raised predicted band-gap targeting from 0% to 24%; a separately trained checkpoint reached 43%. blog code model
Research index
Systems recipes
Rollout serving Optimizing throughput for async RL DeepSeek-V4-Flash serving on two DGX Sparks: 731.5 tok/s sustained on distinct prompts and a separate 1,106 tok/s shared-prefix result after a workspace patch. recipe code
ML systems recipes
Essays and working notes