大模型推理能力

M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models

Junxiong Wang, Wen-Ding Li, Daniele Paliotta, Daniel Ritter, Alexander M. Rush, Tri Dao

机构 * TogetherAI ； Cornell University（康奈尔大学） ； University of Geneva（日内瓦大学） ； Princeton University（普林斯顿大学） 纠错

专题命中 测试时计算 ：reasoning(title,abstract)；test-time compute(title)；chain-of-thought(abstract)；分类 cs.LG

Comments Code is available https://github.com/jxiw/M1

Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models

Kaiyan Chang, Yonghao Shi, Chenglong Wang, Hang Zhou, Chi Hu, Xiaoqian Liu, Yingfeng Luo, Yuan Ge, Tong Xiao, Jingbo Zhu

机构 * School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院） ； NiuTrans Research（NiuTrans研究院） ； ByteDance（字节跳动） 纠错

专题命中 测试时计算 ：verifier(title)；reasoning(abstract)；分类 cs.CL

Comments Accepted by EMNLP 2025. Code: https://github.com/Lucky-259/Hybrid_TTS

Instruction Agent: Enhancing Agent with Expert Demonstration

Yinheng Li, Hailey Hultquist, Justin Wagle, Kazuhito Koishida

机构 * Microsoft（微软公司） 纠错

专题命中 测试时计算 ：verifier(abstract)；分类 cs.CL、cs.AI