arXiv:2605. 13511v3 Announce Type: replace-cross Abstract: While many-shot ICL achieves remarkable performance, prior studies of its scaling behavior have mainly focused on non-reasoning tasks.
By Tsz Ting Chung, Lemao Liu, Mo Yu, Dit-Yan Yeung
arXiv:2601. 03506v2 Announce Type: replace-cross Abstract: Recent large reasoning models (LRMs) have achieved strong performance on complex reasoning tasks by generating a long chain-of-thought (Long-CoT).
By Zhaofeng Zhong, Wei Yuan, Tong Chen, Liang Qu, Xiangyu Zhao, Quoc Viet Hung Nguyen, Hongzhi Yin
The paper introduces Prototype-Mediated Process Supervision (PMPS), a method that uses learnable reasoning prototypes to provide structural supervision for latent chain-of-thought embeddings, addressing representation collapse and uneven information distribution. PMPS aligns latent and explicit CoT embeddings in a shared prototype space via many-to-many soft assignment and employs a Progressive Sequential Alignment module to guide training from positional priors to adaptive matching. Experiments show PMPS reduces output token length to under 50% of explicit CoT on GSM8K-Aug and improves accuracy by 2.08% over SIM-CoT, even surpassing CoT-SFT on GPT-2 and achieving the highest accuracy among latent reasoning methods on larger models and harder tasks.
By Yiqi Li, Xu Chen, Chen Ju, Jiangchao Yao, Zhaoyang Li, Jinsong Lan, Xiaoyong Zhu, Bo Zheng, Yu Wang
arXiv:2602. 23161v4 Announce Type: replace Abstract: Time series reasoning demands both the perception of complex dynamics and logical depth.
By Junkai Lu, Peng Chen, Xingjian Wu, Yang Shu, Chenjuan Guo, Christian S. Jensen, Bin Yang
SPEAR (Symbolic Process Evaluation and Alignment Reward) is a training‑free, plug‑and‑play reward method for on‑policy distillation in reinforcement learning. It converts natural‑language reasoning traces into domain‑adaptive symbolic milestones and uses the longest common subsequence to align student exploration with teacher milestones, producing a dense, order‑aware reward that enforces logical consistency without an external neural verifier. Experiments on math, science, and commonsense reasoning tasks show that SPEAR effectively bridges the reasoning gap between student and teacher models through sequence‑level distillation with efficient dense process rewards.
By Zhuochun Li, Yuelyu Ji, Yiming Zeng, Daqing He
arXiv:2604. 10788v2 Announce Type: replace-cross Abstract: Tool-Integrated Reasoning (TIR) has emerged as a promising direction by extending Large Language Models' (LLMs) capabilities with external tools during reasoning.
By Qiancheng Xu, Yongqi Li, Fan Liu, Hongru Wang, Min Yang, Wenjie Li