Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following
This addresses the challenge of sparse rewards in multi-constraint tasks for real-world applications, though it is incremental as it builds on existing RL methods.
The paper tackles the problem of language models struggling with multi-constraint instruction following by proposing a self-supervised reinforcement learning framework that eliminates external supervision, achieving strong improvements across 3 in-domain and 5 out-of-domain datasets.
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 training. Our approach introduces constraint decomposition strategies and efficient constraint-wise binary classification to address sparse reward challenges while maintaining computational efficiency. Experiments show that our approach generalizes well, achieving strong improvements across 3 in-domain and 5 out-of-domain datasets, including challenging agentic and multi-turn instruction following. The data and code are publicly available at https://github.com/Rainier-rq/verl-if