The Q* hypothesis: Tree-of-thoughts reasoning, process reward models, and supercharging synthetic data

core components of Deep RL that enabled success like AlphaGo: self-play and look-ahead planning.

Self-play is the idea that an agent can improve its gameplay by playing against slightly different versions of itself because it’ll progressively encounter more challenging situations. In the space of LLMs, it is almost certain that the largest portion o... See more