Reka AI treats tool useA model's ability to call external functions — run code, search the web, edit files — instead of only generating text.Full definition → as something a reasoning modelA model trained to think — generating extended internal reasoning before answering — trading time and tokens for accuracy on hard problems.Full definition → should learn through practice. Its research account describes starting with supervised examples, then using reinforcement learning in which the model takes actions and receives feedback. For a coding task, that can mean executing proposed code and using the result to guide training. The same approach underlies its stated work on browsing and document research. This makes the training problem include choosing and interpreting tools, while introducing an infrastructure challenge: waiting for external tools slows the feedback loop.
Terms in this piece · Glossary
tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.
reasoning model — A model trained to think — generating extended internal reasoning before answering — trading time and tokens for accuracy on hard problems.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
