Beyond The Trade-off: Self-supervised Reinforcement Learning For Reasoning Models’ Instruction Following | Awesome LLM Papers Add your paper to Awesome LLM Papers

Awesome LLM Papers

A continuously updated collection of research papers on LLMs.

Stay Updated

Contact Sean Moran about this survey or website. Made with Jekyll and Hyde.

Beyond The Trade-off: Self-supervised Reinforcement Learning For Reasoning Models' Instruction Following

Qingyu Ren, Qianyu He, Bowei Zhang, Jie Zeng, Jiaqing Liang, Yanghua Xiao, Weikang Zhou, Zeye Sun, Fei Yu . No Venue 2025

[Code] [Paper]   Search on Google Scholar   Search on Semantic Scholar
Compositional Generalization Has Code Instruction Following Productivity Enhancement Reinforcement Learning Tools Training Techniques

Reasoning models excel in complex problem solving but exhibit a concerning trade off between reasoning capabilities and instruction following abilities. Existing approaches for improving instruction following rely on stronger external models, creating methodological bottlenecks and practical limitations including increased costs and accessibility constraints. We propose a self-supervised RL framework that leverages reasoning models’ own internal signals to improve instruction following capabilities without external supervision. Extensive experiments demonstrate that our framework significantly improves instruction following capabilities while maintaining reasoning performance, offering a scalable and cost-effective approach to enhance instruction following in reasoning models. The data and code are publicly available at https://github.com/Rainier-rq/verl-if.

Similar Work