https://github.com/TauricResearch/TradingAgents

SkyDreamer: Interpretable End-to-End Vision-Based Drone Racing with Model-Based Reinforcement Learning https://arxiv.org/abs/2510.14783

Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following https://arxiv.org/abs/2510.14420

AlphaArena https://nof1.ai/

(Я с черными дырами работаю)

Было бы интересно