CC-LEARN: Cohort-based Consistency Learning

Large language models excel at many tasks but still struggle with consistent, robust reasoning. We introduce Cohort-based Consistency Learning (CC-Learn), a reinforcement learning framework that improves the reliability of LLM reasoning by training on cohorts of similar questions derived from shared programmatic abstractions. To enforce cohort-level consistency, we define a composite objective combining cohort accuracy, a retrieval bonus for effective problem decomposition, and a rejection penalty for trivial or invalid lookups that reinforcement learning can directly optimize, unlike supervised fine-tuning. Optimizing this reward guides the model to adopt uniform reasoning patterns across all cohort members. Experiments on challenging reasoning benchmarks (including ARC-Challenge and StrategyQA) show that CC-Learn boosts both accuracy and reasoning stability over pretrained and SFT baselines. These results demonstrate that cohort-level RL effectively enhances reasoning consistency in LLMs.

@article{ye2025_2506.15662,
  title={ CC-LEARN: Cohort-based Consistency Learning },
  author={ Xiao Ye and Shaswat Shrivastava and Zhaonan Li and Jacob Dineen and Shijie Lu and Avneet Ahuja and Ming Shen and Zhikun Xu and Ben Zhou },
  journal={arXiv preprint arXiv:2506.15662},
  year={ 2025 }
}