Activation steering finds better reasoning paths under the same RL budget
Activation-Space Exploration helps language models search more varied reasoning paths during reinforcement learning on automatically verifiable tasks, without increasing the rollout budget. It clusters activation differences between correct and incorrect answers to the same problem, then applies the resulting latent vectors to later rollouts. On six math benchmarks, it improved Mean@8 over GRPO by 4.87 points for Qwen3-1.7B-Base and 1.87 points for Qwen3-8B-Base.