Jarrod Barnes

I'm a researcher and founder working on open-ended scientific discovery.

I run Dynamical Systems, where I build environments, evaluations, and verification systems that make open-ended scientific work trainable.

Research threads

Scientific discovery Training scientific judgment Verified campaign environments convert search, trust, escalation, and revision into a multi-turn RL problem with physics-grounded oracle reward. Verification Scaling test-time verification for novel materials Probe-gradient guidance extracts band-gap signal from an unconditional crystal diffusion model and steers sampling without retraining. Post-training Self-improving pretraining as a substrate for agentic post-training I adapted self-improving pretraining, interleaved-thought SFT, and RL mid-training to Qwen3-0.6B-Base. Interpretability Do language models know when to change their mind? Signal detection framework for LLM belief revision across six open-weight models. Learning systems Continual learning for production agents ATLAS converts production agent trajectories into inference-time learning and on-policy distillation loops.

Research index

More writing

A Theory On Becoming an Expert Learning systems / May 4, 2026 Rethinking Evaluation for Agents That Never Stop Learning Evaluation / Jan 13, 2026 Building a World Model of Consequence Learning systems / Nov 19, 2025 My Agents Keep Failing. Yours Will Too. Learning systems / Jul 16, 2025 Everything is Changing...Again Learning systems / Apr 30, 2025

All writing