Distill the principles.
Draw on existing neuroscience research to identify computational mechanisms for learning, memory, and the coordination of search.
We pursue two connected lines of research to build state-of-the-art,
commercially deployable systems.
Draw on existing neuroscience research to identify computational mechanisms for learning, memory, and the coordination of search.
Investigate the mechanics of large language models to turn those principles into algorithms and working systems.
A research program connecting learning, episodic memory, and explicit search to build more powerful adaptive intelligence.
We introduce Dynamic Compute Allocation (DCA) and evaluate it on agentic coding tasks, across pure and composite model configurations, on Terminal-Bench 2.0.
Perturbing a small fraction of routing decisions in frozen MoE reasoning models—a little noise helped, a lot hurt, and the tuning curve suggests a new search surface inside the model.
We hold model weights and prompts fixed, and explore everything else. Our research discovers levers within LLMs that improve reasoning at test time, guided by computational principles drawn from neuroscience.
AI today encodes intelligence into weights and retrieves it at inference. Hard problems demand more: active reasoning that balances accuracy with efficiency, and knows when to think harder.