大模型推理能力 - arXivDaily 专题

2506.08935 2025-06-11 cs.CL cs.AI cs.LG 82%

Can A Gamer Train A Mathematical Reasoning Model?

Andrew Shin

机构 * Keio University（庆应大学）

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

2501.18858 2025-06-10 cs.LG cs.AI cs.CL 82%

BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning

Han Zhong, Yutong Yin, Shenao Zhang, Xiaojun Xu, Yuanxin Liu, Yifei Zuo, Zhihan Liu, Boyi Liu, Sirui Zheng, Hongyi Guo, Liwei Wang, Mingyi Hong, Zhaoran Wang

机构 * Peking University（北京大学）； Northwestern University（西北大学）； Bytedance Inc（字节跳动公司）； University of Minnesota（明尼苏达大学）

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

Comments ICML 2025

2505.16400 2025-06-06 cs.LG cs.AI cs.CL 82%

AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning

Yang Chen, Zhuolin Yang, Zihan Liu, Chankyu Lee, Peng Xu, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping

机构 * NVIDIA

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

Comments Add pass@1024 evaluation results for LiveCodeBench v6. We release the models at: https://huggingface.co/collections/nvidia/acereason-682f4e1261dc22f697fd1485

2505.22591 2025-05-29 cs.CL cs.AI cs.LG 82%

Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning

Erxin Yu, Jing Li, Ming Liao, Qi Zhu, Boyang Xue, Minghui Xu, Baojun Wang, Lanqing Hong, Fei Mi, Lifeng Shang

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

Comments 16 pages, 9 figures

2412.06559 2025-05-27 cs.AI cs.CL cs.LG 82%

ProcessBench: Identifying Process Errors in Mathematical Reasoning

Chujie Zheng, Zhenru Zhang, Beichen Zhang, Runji Lin, Keming Lu, Bowen Yu, Dayiheng Liu, Jingren Zhou, Junyang Lin

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

Comments ACL 2025

2505.17250 2025-05-26 cs.CL cs.AI cs.LG 82%

ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models

Razvan-Gabriel Dumitru, Darius Peteleaza, Vikas Yadav, Liangming Pan

机构 * First Author Affiliation（第一作者机构）； Second Author Affiliation（第二作者机构）

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

Comments 25 pages, 18 figures, and 6 tables

2505.13417 2025-05-20 cs.CL cs.AI cs.LG 82%

AdaptThink: Reasoning Models Can Learn When to Think

Jiajie Zhang, Nianyi Lin, Lei Hou, Ling Feng, Juanzi Li

机构 * Tsinghua University（清华大学）

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

2505.03981 2025-05-09 cs.AI cs.CL cs.LG 82%

X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains

Qianchu Liu, Sheng Zhang, Guanghui Qin, Timothy Ossowski, Yu Gu, Ying Jin, Sid Kiblawi, Sam Preston, Mu Wei, Paul Vozila, Tristan Naumann, Hoifung Poon

机构 * Microsoft Research（微软研究院）

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

2504.20708 2025-04-30 cs.CL cs.AI cs.LG 82%

Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think

Hasan Abed Al Kader Hammoud, Hani Itani, Bernard Ghanem

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

Comments Preprint

2504.16891 2025-04-24 cs.AI cs.CL cs.LG 82%

AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset

Ivan Moshkov, Darragh Hanley, Ivan Sorokin, Shubham Toshniwal, Christof Henkel, Benedikt Schifferer, Wei Du, Igor Gitman

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

Comments Report of AIMO-2 winning submission

2407.05952 2025-04-08 cs.DB cs.AI cs.CL cs.LG 82%

H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables

Nikhil Abhyankar, Vivek Gupta, Dan Roth, Chandan K. Reddy

机构 * Virginia Tech（弗吉尼亚理工大学）； Arizona State University（亚利桑那州立大学）； University of Pennsylvania（宾夕法尼亚大学）

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

Comments NAACL 2025 Main Conference

2502.08680 2025-02-14 cs.LG cs.AI cs.CL 82%

Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges

Safal Shrestha, Minwu Kim, Keith Ross

机构 * New York University Abu Dhabi（纽约大学阿布扎比分校）

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

2411.19943 2025-01-14 cs.CL cs.AI cs.LG 82%

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability

Zicheng Lin, Tian Liang, Jiahao Xu, Qiuzhi Lin, Xing Wang, Ruilin Luo, Chufan Shi, Siheng Li, Yujiu Yang, Zhaopeng Tu

机构 * Tencent AI Lab（腾讯AI实验室）

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

Comments Work in progress

2501.00823 2025-01-07 cs.LG cs.AI cs.CL 82%

Decoupling Knowledge and Reasoning in Transformers: A Modular Architecture with Generalized Cross-Attention

Zhenyu Guo, Wenguang Chen

机构 * Tsinghua University（清华大学）； Ant Group（蚂蚁集团）

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

2412.19707 2024-12-30 cs.AI cs.CL cs.LG 82%

Toward Adaptive Reasoning in Large Language Models with Thought Rollback

Sijia Chen, Baochun Li

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

Comments ICML 2024 camera-ready version with 24 pages and 12 figures. Code repo with all prompts: https://github.com/iQua/llmpebase/tree/main/examples/ThoughtRollback

2411.19500 2024-12-02 cs.CL cs.AI cs.LG 82%

COLD: Causal reasOning in cLosed Daily activities

Abhinav Joshi, Areeb Ahmad, Ashutosh Modi

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

Comments Paper accepted at NeurIPS 2024; Total 37 Pages

2410.15115 2024-11-28 cs.LG cs.AI cs.CL 82%

On Designing Effective RL Reward at Training Time for LLM Reasoning

Jiaxuan Gao, Shusheng Xu, Wenjie Ye, Weilin Liu, Chuyi He, Wei Fu, Zhiyu Mei, Guangju Wang, Yi Wu

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

2405.14039 2024-10-31 cs.CL cs.AI cs.LG 82%

Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning

Yiming Wang, Pei Zhang, Baosong Yang, Derek F. Wong, Zhuosheng Zhang, Rui Wang

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

Comments Accepted by NeurIPS 2024

2410.10858 2024-10-16 cs.CL cs.AI cs.LG 82%

Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths

Yew Ken Chia, Guizhen Chen, Weiwen Xu, Luu Anh Tuan, Soujanya Poria, Lidong Bing

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

Comments EMNLP 2024 camera ready version

2409.19044 2024-10-01 cs.CL cs.AI cs.LG 82%

On the Inductive Bias of Stacking Towards Improving Reasoning

Nikunj Saunshi, Stefani Karp, Shankar Krishnan, Sobhan Miryoosefi, Sashank J. Reddi, Sanjiv Kumar

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

Comments Accepted at NeurIPS 2024

2407.20311 2024-07-31 cs.AI cs.CL cs.LG 82%

Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process

Tian Ye, Zicheng Xu, Yuanzhi Li, Zeyuan Allen-Zhu

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

Comments video appeared in ICML 2024 tutorial

2312.04474 2024-07-31 cs.CL cs.AI cs.LG cs.RO 82%

Chain of Code: Reasoning with a Language Model-Augmented Code Emulator

Chengshu Li, Jacky Liang, Andy Zeng, Xinyun Chen, Karol Hausman, Dorsa Sadigh, Sergey Levine, Li Fei-Fei, Fei Xia, Brian Ichter

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

Comments ICML 2024 Oral; Project webpage: https://chain-of-code.github.io

2403.02178 2024-07-12 cs.CL cs.AI cs.LG 82%

Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models

Changyu Chen, Xiting Wang, Ting-En Lin, Ang Lv, Yuchuan Wu, Xin Gao, Ji-Rong Wen, Rui Yan, Yongbin Li

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

Comments Accepted by ACL 2024

2407.01284 2024-07-02 cs.AI cs.CL cs.CV cs.LG cs.SC 82%

We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?

Runqi Qiao, Qiuna Tan, Guanting Dong, Minhui Wu, Chong Sun, Xiaoshuai Song, Zhuoma GongQue, Shanglin Lei, Zhe Wei, Miaoxuan Zhang, Runfeng Qiao, Yifan Zhang, Xiao Zong, Yida Xu, Muxi Diao, Zhimin Bao, Chen Li, Honggang Zhang

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

Comments Work in progress

2406.18629 2024-06-28 cs.LG cs.AI cs.CL 82%

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Xin Lai, Zhuotao Tian, Yukang Chen, Senqiao Yang, Xiangru Peng, Jiaya Jia

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

Comments Code, data, and models are available at https://github.com/dvlab-research/Step-DPO

2309.13007 2024-06-25 cs.CL cs.AI cs.LG 82%

ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs

Justin Chih-Yao Chen, Swarnadeep Saha, Mohit Bansal

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

Comments ACL 2024 (Camera-Ready)

2406.10834 2024-06-18 cs.CL cs.AI cs.LG 82%

Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning

Joykirat Singh, Akshay Nambi, Vibhav Vineet

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

2308.07758 2024-06-06 cs.CL cs.AI cs.LG 82%

Forward-Backward Reasoning in Large Language Models for Mathematical Verification

Weisen Jiang, Han Shi, Longhui Yu, Zhengying Liu, Yu Zhang, Zhenguo Li, James T. Kwok

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

Comments Accepted by Findings of ACL 2024

2406.00755 2024-06-05 cs.CL cs.AI cs.LG 82%

Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction

Xiaoyuan Li, Wenjie Wang, Moxin Li, Junrong Guo, Yang Zhang, Fuli Feng

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

Comments ACL Findings 2024

2402.03300 2024-04-30 cs.CL cs.AI cs.LG 82%

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y. K. Li, Y. Wu, Daya Guo

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

1. 数学推理 3258 篇

Can A Gamer Train A Mathematical Reasoning Model?

BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning

AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning

Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning

ProcessBench: Identifying Process Errors in Mathematical Reasoning

ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models

AdaptThink: Reasoning Models Can Learn When to Think

X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains

Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think

AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset

H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables

Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability

Decoupling Knowledge and Reasoning in Transformers: A Modular Architecture with Generalized Cross-Attention

Toward Adaptive Reasoning in Large Language Models with Thought Rollback

COLD: Causal reasOning in cLosed Daily activities

On Designing Effective RL Reward at Training Time for LLM Reasoning

Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning

Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths

On the Inductive Bias of Stacking Towards Improving Reasoning

Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process

Chain of Code: Reasoning with a Language Model-Augmented Code Emulator

Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models

We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs

Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning

Forward-Backward Reasoning in Large Language Models for Mathematical Verification

Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models