Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following

ArXi:2510.14420v4 Announce Type: replace-cross Language models often struggle to follow multi-constraint instructions that are crucial for real-world applications. Existing reinforcement learning (RL) approaches suffer from dependency on external supervision and sparse reward signals from multi-constraint tasks. We propose a label-free self-supervised RL framework that eliminates dependency on external supervision by deriving reward signals directly from instructions and generating pseudo-labels for reward model.