大模型推理能力

GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements

Alex Havrilla, Sharath Raparthy, Christoforus Nalmpantis, Jane Dwivedi-Yu, Maksym Zhuravinskyi, Eric Hambro, Roberta Raileanu

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.LG

Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation

Chengwei Dai, Kun Li, Wei Zhou, Songlin Hu

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Arithmetic Reasoning with LLM: Prolog Generation & Permutation

Xiaocheng Yang, Bingsen Chen, Yik-Cheung Tam

专题命中 数学推理 ：reasoning(title)；CoT(abstract)；分类 cs.CL、cs.AI

Comments 12 pages, 4 figures, accepted by NAACL 2024 Main Conference

Premise Order Matters in Reasoning with Large Language Models

Xinyun Chen, Ryan A. Chi, Xuezhi Wang, Denny Zhou

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments Published at ICML 2024. Xinyun and Ryan contribute equally

JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models

Kun Zhou, Beichen Zhang, Jiapeng Wang, Zhipeng Chen, Wayne Xin Zhao, Jing Sha, Zhichao Sheng, Shijin Wang, Ji-Rong Wen

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments 28 pages, SOTA math LLM using Well-trained Data Synthesis LLM

Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in Large Language Models

Yue Zhou, Yada Zhu, Diego Antognini, Yoon Kim, Yang Zhang

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments Accepted to the main conference of NAACL (2024)

A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers

Jordan Meadows, Marco Valentino, Damien Teney, Andre Freitas

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.LG

Comments NAACL 2024

Look Before You Leap: Problem Elaboration Prompting Improves Mathematical Reasoning in Large Language Models

Haoran Liao, Jidong Tian, Shaohua Hu, Hao He, Yaohui Jin

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models

Yanan Wu, Jie Liu, Xingyuan Bu, Jiaheng Liu, Zhanhui Zhou, Yuanxing Zhang, Chenchen Zhang, Zhiqi Bai, Haibin Chen, Tiezheng Ge, Wanli Ouyang, Wenbo Su, Bo Zheng

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments The benchmark dataset will be released soon

Democratizing Reasoning Ability: Tailored Learning from Large Language Model

Zhaoyang Wang, Shaohan Huang, Yuxuan Liu, Jiahai Wang, Minghui Song, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments To appear at EMNLP 2023

A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis

Alessandro Stolfo, Yonatan Belinkov, Mrinmaya Sachan

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.LG

Comments EMNLP 2023. 18 pages, 19 figures

Getting MoRE out of Mixture of Language Model Reasoning Experts

Chenglei Si, Weijia Shi, Chen Zhao, Luke Zettlemoyer, Jordan Boyd-Graber

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments EMNLP 2023 Findings

MAF: Multi-Aspect Feedback for Improving Reasoning in Large Language Models

Deepak Nathani, David Wang, Liangming Pan, William Yang Wang

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments Accepted at EMNLP 2023 Main Conference, Camera Ready

GPT-3.5, GPT-4, or BARD? Evaluating LLMs Reasoning Ability in Zero-Shot Setting and Performance Boosting Through Prompts

Jessica López Espejel, El Hassane Ettifouri, Mahaman Sanoussi Yahaya Alassan, El Mehdi Chouham, Walid Dahhane

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments Accepted for publication at Elsevier's Natural Language Processing Journal

MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning

Zhenwen Liang, Dian Yu, Xiaoman Pan, Wenlin Yao, Qingkai Zeng, Xiangliang Zhang, Dong Yu

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models

Alessandro Stolfo, Zhijing Jin, Kumar Shridhar, Bernhard Schölkopf, Mrinmaya Sachan

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.LG

Comments ACL 2023. A shorter version of the paper was accepted at the MATH-AI Workshop at NeurIPS 2022. 15 pages, 8 figures

Interpretable Math Word Problem Solution Generation Via Step-by-step Planning

Mengxue Zhang, Zichao Wang, Zhichao Yang, Weiqi Feng, Andrew Lan

专题命中 数学推理 ：planning(title,abstract)；分类 cs.CL、cs.AI

Comments Accepted to The 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023)

DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data

Xiao Li, Yin Zhu, Sichen Liu, Jiangzhou Ju, Yuzhong Qu, Gong Cheng

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments 9 pages, accepted by AAAI 2023

LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning

Yuhuai Wu, Markus Rabe, Wenda Li, Jimmy Ba, Roger Grosse, Christian Szegedy

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.AI、cs.LG

Comments Published as a conference paper at ICML 2021 (16 pages)

Contrastive Reasoning in Neural Networks

Mohit Prabhushankar, Ghassan AlRegib

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.AI、cs.LG

Comments Submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence

Interactive Learning for LLM Reasoning

为LLM推理设计的交互学习

Hehai Lin, Shilei Cao, Sudong Wang, Haotian Wu, Minzhi Li, Linyi Yang, Juepeng Zheng, Chengwei Qin

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Sun Yat-sen University（中山大学） ； Southern University of Science and Technology（南方科技大学） ； National University of Singapore（新加坡国立大学） 纠错

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.AI

AI总结 本文提出ILR框架，通过动态交互和感知校准提升LLM独立问题解决能力，实验表明其在多个基准测试中优于单agent学习。

Comments The code is available at https://github.com/linhh29/Interactive-Learning-for-LLM-Reasoning

Reliable Self-Improvement Training by Verifying Reasoning, Not Just Answers

可靠的自改进训练：验证推理过程，而不仅仅是答案

Xinyu Zhang

机构 * Anyscale 纠错

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.AI

AI总结 针对自改进训练中因依赖最终答案正确性导致推理错误累积的问题，提出VSI框架，通过步骤级结构验证（如符号计算检查算术步骤）筛选训练数据，在GSM8K上实现持续准确率提升（80.5%→91.0%）。

Comments Accepted at ICLR 2026 Workshop LLM Reasoning. 10 pages, 3 figures, 5 tables

The Impact of Quantization on Large Reasoning Model Reinforcement Learning

量化对大推理模型强化学习的影响

Medha Kumar, Zifei Xu, Xin Wang, Tristan Webb

机构 * Pennsylvania State University（宾夕法尼亚州立大学） ； d-Matrix 纠错

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.LG

AI总结 本文研究了量化对大推理模型强化学习的影响，发现量化感知训练对学习过程有负面影响，而PTQ和QLoRA能提升性能。

Comments Accepted to the NeurIPS 2025 Efficient Reasoning Workshop

RLP: Reinforcement as a Pretraining Objective

RLP：将强化学习作为预训练目标

Ali Hatamizadeh, Syeda Nahida Akter, Shrimai Prabhumoye, Jan Kautz, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Yejin Choi

机构 * NVIDIA（英伟达） ； Carnegie Mellon University（卡内基梅隆大学） ； Boston University（波士顿大学） ； Stanford University（斯坦福大学） 纠错

专题命中 数学推理 ：reasoning(abstract)；chain-of-thought(abstract)；verifier(abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结 RLP通过将强化学习的探索精神引入预训练阶段，提升模型在数学和科学任务中的推理能力。

Comments ICLR 2026 camera ready

Reinforcement Learning for Chain of Thought Compression with One-Domain-to-All Generalization

基于单领域到全领域泛化的强化学习进行思维链压缩

Hanyu Li, Jiangshan Duo, Bofei Gao, Hailin Zhang, Sujian Li, Xiaotie Deng, Liang Zhao

机构 * CFCS, School of Computer Science, Peking University（计算机学院，北京大学） ； State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机学院，北京大学） ； LLM-Core Xiaomi（小米LLM-Core） 纠错

专题命中 数学推理 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结 本文提出了一种基于单领域到全领域泛化的强化学习方法，通过样本级软强化学习压缩思维链推理，有效减少响应长度并提升跨领域泛化能力。

SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts

SPEC-RL: 通过推测性回放加速在线策略学习

Bingshuai Liu, Ante Wang, Zijun Min, Liang Yao, Haibo Zhang, Yang Liu, Xu Han, Peng Li, Anxiang Zeng, Jinsong Su

机构 * School of Informatics, Xiamen University（厦门大学信息学院） ； LLM Team, Shopee Pte. Ltd.（Shopee公司语言模型团队） ； Tsinghua University（清华大学） 纠错

专题命中 数学推理 ：reasoning(abstract)；chain-of-thought(abstract)；math reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结 SPEC-RL通过整合推测解码技术，有效减少强化学习回放阶段的计算开销，提升大模型推理能力。

Comments fixed typos

All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language

Shiyuan Guo, Henry Sleight, Fabien Roger

机构 * Anthropic Fellows Program（Anthropic Fellow项目） ； Constellation ； Anthropic 纠错

专题命中 数学推理 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Version 2: updated related works section on LLM steganography

Merge-of-Thought Distillation

Zhanming Shen, Zeyu Qin, Zenan Huang, Hao Chen, Jiaqi Hu, Yihong Zhuang, Guoshan Lu, Gang Chen, Junbo Zhao

机构 * Zhejiang University（浙江大学） ； Inclusion AI, Ant Group（蚂蚁集团 inclusion AI） 纠错

专题命中 数学推理 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI、cs.LG

Dynamic Policy Induction for Adaptive Prompt Optimization: Bridging the Efficiency-Accuracy Gap via Lightweight Reinforcement Learning

Jiexi Xu

机构 * University of California, Irvine School of Information & Computer Science（加州大学尔湾分校信息与计算机科学学院） 纠错

专题命中 数学推理 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 13 pages, 2 figures, 2 tables

SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Weihao Zeng, Yuzhen Huang, Qian Liu, Wei Liu, Keqing He, Zejun Ma, Junxian He

专题命中 数学推理 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Published as a conference paper at COLM 2025