fine-tuning — Taking a trained model and training it a bit more on your own examples so it gets better at one specific job.
chain-of-thought — Having a model write out intermediate reasoning steps before its answer, which markedly improves performance on hard problems.
pretraining — The first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.
token budget — A cap on how many tokens a task, session, or agent run may consume — the practical control on both cost and how long an agent will grind.
Why it matters
Shows a small chat model can acquire strong math reasoning from post-training alone, and that short-horizon RL is what makes the chains concise enough to fit an edge response budget.
