Tag
Tahuna is an open-source AI training infrastructure designed for small teams to train models, run inference, orchestrate GPUs, and experiment with autonomous research, featuring reproducible runs and tools like Hillclimb.
This paper proposes replacing the stateless autoresearch pattern with a stateful ReAct agent using LangGraph, reducing per-iteration token costs from O(n) to O(1) and achieving 52-90% fewer tokens on hyperparameter tuning and code optimization benchmarks.