Chi Zhang, Mengqi Zhang, Xiaotian Ye, Runxi Cheng, Zisheng Zhou, Ying Zhou, Pengjie Ren, Zhumin Chen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Self-taught reasoners (STaRs) enhance the mathematical reasoning abilities of large language models (LLMs) by leveraging selfgenerated responses for self-training.Recent studies have incorporated reward models to guide response selection or decoding, aiming to obtain higher-quality data.However, they typically allocate a uniform sampling budget across all problems, overlooking the varying utility of problems at different difficulty levels.In this work, we conduct an empirical study and find that problems near the boundary of the LLM's reasoning capability offer significantly greater learning utility than both easy and overly difficult ones.To identify and exploit such problems, we propose HS-STAR, a Hierarchical Sampling framework for Self-Taught Reasoners.Given a fixed sampling budget, HS-STAR first performs lightweight presampling with a reward-guided difficulty estimation strategy to efficiently identify boundarylevel problems.Subsequently, it dynamically reallocates the remaining budget toward these high-utility problems during a re-sampling phase, maximizing the generation of valuable training data.Extensive experiments across multiple reasoning benchmarks and backbone LLMs demonstrate that HS-STAR significantly outperforms other baselines without requiring additional sampling budget.78 81 84 87 GSM8K 80.1 81.0 79.5 81.1 80.2 79.9 82.8 80.

Model merging seeks to integrate task-specific expert models into a unified architecture while preserving multi-task generalization capabilities, yet parameter interference between constituent models frequently induces performance degradation. Although prior work has explored many merging strategies, resolving interference without additional data for retraining or test-time computation remains challenging. In this paper, we theoretically demonstrate that the task vectors of the linear layer constitute an approximate linear subspace for its corresponding input. Therefore, we can minimize interference under the guidance of task vectors. Based on this insight, we propose WUDI-Merging (Whoever started the interference shoUld enD It), a simple yet effective model merging method that eliminates interference without any additional data or rescaling coefficients. Comprehensive empirical evaluations across vision and language benchmarks demonstrate our method’s superiority, achieving state-of-the-art performance in data-free model merging scenarios (average 10.9% improvement versus baseline methods) while even outperforming mainstream test-time adaptation approaches by 3.3%, and only very few computing resources are required. The source code and implementation details are available at https://github.com/nathanielyvo/WUDI-Merging.

Knowledge distillation typically minimizes the Kullback–Leibler (KL) divergence between teacher and student logits. However, optimizing the KL divergence can be challenging for the student and often leads to sub-optimal solutions. We further show that gradients induced by KL divergence scale with the magnitude of the teacher logits, thereby diminishing updates on low-probability channels. This imbalance weakens the transfer of inter-class information and in turn limits the performance improvements achievable by the student. To mitigate this issue, we propose a plug-and-play auxiliary ranking loss based on Kendall’s $\tau$ coefficient that can be seamlessly integrated into any logit-based distillation framework. It supplies inter-class relational information while rebalancing gradients toward low-probability channels. We demonstrate that the proposed ranking loss is largely invariant to channel scaling and optimizes an objective aligned with that of KL divergence, making it a natural complement rather than a replacement. Extensive experiments on CIFAR-100, ImageNet, and COCO datasets, as well as various CNN and ViT teacher-student architecture combinations, demonstrate that our plug-and-play ranking loss consistently boosts the performance of multiple distillation baselines.