语言大模型 / LLM

PersonaBOT: Bringing Customer Personas to Life with LLMs and RAG

Muhammed Rizwan, Lars Carlsson, Mohammad Loni

机构 * Department of Computer Science, Jönköping University（计算机科学系，约翰科普ิง大学） ； Department of Future Solutions, Volvo Construction Equipment（未来解决方案部，沃尔沃建筑设备公司） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.LG

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

Zhiwei He, Tian Liang, Jiahao Xu, Qiuzhi Liu, Xingyu Chen, Yue Wang, Linfeng Song, Dian Yu, Zhenwen Liang, Wenxuan Wang, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu

机构 * Tencent（腾讯） ； Shanghai Jiao Tong University（上海交通大学） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；SFT(abstract)；分类 cs.CL、cs.AI

Comments WIP

DayDreamer at CQs-Gen 2025: Generating Critical Questions through Argument Scheme Completion

Wendi Zhou, Ameer Saadat-Yazdi, Nadin Kökciyan

机构 * School of Informatics, University of Edinburgh（信息学院，爱丁堡大学） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Comments ArgMining 2025 CQs-Gen shared task

The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles

Vernon Y. H. Toh, Yew Ken Chia, Deepanway Ghosal, Soujanya Poria

机构 * Singapore University of Technology and Design（新加坡科技设计大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review

Zhuochun Li, Yuelyu Ji, Rui Meng, Daqing He

机构 * School of Computing and Information, University of Pittsburgh（计算与信息学院，匹兹堡大学） ； Salesforce Research（Salesforce 研究） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments 16 pages, 5 figures

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards

Xiaoyuan Liu, Tian Liang, Zhiwei He, Jiahao Xu, Wenxuan Wang, Pinjia He, Zhaopeng Tu, Haitao Mi, Dong Yu

机构 * Tencent（腾讯） ； CUHK（香港中文大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments code available at https://github.com/xyliu-cs/RISE

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning

Qiguang Chen, Libo Qin, Jinhao Liu, Yue Liao, Jiaqi Wang, Jingxuan Zhou, Wanxiang Che

机构 * Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology（社会计算与交互机器人研究中心，哈尔滨工业大学） ； Faculty of Computing, Harbin Institute of Technology（计算学院，哈尔滨工业大学） ； School of Computer Science and Engineering, Central South University（计算机科学与工程学院，中南大学） ； Chinese University of Hong Kong（香港中文大学） ； MMLab, The Chinese University of Hong Kong（香港中文大学MMLab） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Manuscript

Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

NVIDIA, :, Alisson Azzolini, Junjie Bai, Hannah Brandon, Jiaxin Cao, Prithvijit Chattopadhyay, Huayu Chen, Jinju Chu, Yin Cui, Jenna Diamond, Yifan Ding, Liang Feng, Francesco Ferroni, Rama Govindaraju, Jinwei Gu, Siddharth Gururani, Imad El Hanafi, Zekun Hao, Jacob Huffman, Jingyi Jin, Brendan Johnson, Rizwan Khan, George Kurian, Elena Lantz, Nayeon Lee, Zhaoshuo Li, Xuan Li, Maosheng Liao, Tsung-Yi Lin, Yen-Chen Lin, Ming-Yu Liu, Xiangyu Lu, Alice Luo, Andrew Mathau, Yun Ni, Lindsey Pavao, Wei Ping, David W. Romero, Misha Smelyanskiy, Shuran Song, Lyne Tchapmi, Andrew Z. Wang, Boxin Wang, Haoxiang Wang, Fangyin Wei, Jiashu Xu, Yao Xu, Dinghao Yang, Xiaodong Yang, Zhuolin Yang, Jingxu Zhang, Xiaohui Zeng, Zhe Zhang

机构 * NVIDIA 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；SFT(abstract)；分类 cs.AI、cs.LG

RLAP: A Reinforcement Learning Enhanced Adaptive Planning Framework for Multi-step NLP Task Solving

Zepeng Ding, Dixuan Wang, Ziqin Luo, Guochao Jiang, Deqing Yang, Jiaqing Liang

机构 * Fudan University（复旦大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

VeriReason: Reinforcement Learning with Testbench Feedback for Reasoning-Enhanced Verilog Generation

Yiting Wang, Guoheng Sun, Wanghao Ye, Gang Qu, Ang Li

机构 * Department of Electrical Engineering, University of Maryland（电气工程系，马里兰大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments 11 pages, 2 figures

S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models

Muzhi Dai, Chenxu Yang, Qingyi Si

机构 * Huawei Technologies Co., Ltd.（华为技术有限公司） ； Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；post-training(abstract)；分类 cs.AI、cs.LG

TensorLLM: Tensorising Multi-Head Attention for Enhanced Reasoning and Compression in LLMs

Yuxuan Gu, Wuyang Zhou, Giorgos Iacovides, Danilo Mandic

机构 * Department of Electrical and Electronic Engineering（电子与电气工程系） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

Comments Accpeted for IEEE International Joint Conference on Neural Networks (IJCNN 2025). The code is available at https://github.com/guyuxuan9/TensorLLM

Improving the Reliability of LLMs: Combining CoT, RAG, Self-Consistency, and Self-Verification

Adarsh Kumar, Hwiyoon Kim, Jawahar Sai Nathani, Neil Roy

机构 * Computer Science and Engineering Texas A&M University（计算机科学与工程，德克萨斯农工大学） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

AI Hiring with LLMs: A Context-Aware and Explainable Multi-Agent Framework for Resume Screening

Frank P. -W. Lo, Jianing Qiu, Zeyu Wang, Haibao Yu, Yeming Chen, Gao Zhang, Benny Lo

机构 * Imperial College London（伦敦帝国理工学院） ； The Chinese University of Hong Kong（香港中文大学） ； The University of Hong Kong（香港大学） ； Wedon Education Technologies（韦登教育科技） ； Brest Business School（布雷斯特商学院） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted by CVPR 2025 Workshop

Recursive Decomposition with Dependencies for Generic Divide-and-Conquer Reasoning

Sergio Hernández-Gutiérrez, Minttu Alakuijala, Alexander V. Nikitin, Pekka Marttinen

机构 * Department of Computer Science Aalto University（计算机科学系 阿尔托大学） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.AI、cs.LG

CHORUS: Zero-shot Hierarchical Retrieval and Orchestration for Generating Linear Programming Code

Tasnim Ahmed, Salimur Choudhury

机构 * School of Computing, Queen’s University, Ontario, Canada（计算学院，皇后大学，安大略省，加拿大） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Comments This paper has been accepted for presentation at the 19th Learning and Intelligent Optimization Conference (LION 19)

Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs

Jinyan Su, Jennifer Healey, Preslav Nakov, Claire Cardie

机构 * Cornell University（康奈尔大学） ； Adobe Research（Adobe研究） ； MBZUAI 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；preference optimization(abstract)；分类 cs.CL、cs.AI

Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion

Muzhi Li, Cehao Yang, Chengjin Xu, Xuhui Jiang, Yiyan Qi, Jian Guo, Ho-fung Leung, Irwin King

机构 * IDEA Research, International Digital Economy Academy（IDEA研究室，国际数字经济学院） ； Department of Computer Science & Engineering, The Chinese University of Hong Kong（计算机科学与工程系，香港中文大学） ； Artificial Intelligence Thrust, Hong Kong University of Science and Technology (Guangzhou)（人工智能方向，香港科技大学（广州）） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted by NAACL2025 main

Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs

Mohammad Akbar-Tajari, Mohammad Taher Pilehvar, Mohammad Mahmoody

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments 19 pages, 1 figure, 6 tables

TALES: Text Adventure Learning Environment Suite

Christopher Zhang Cui, Xingdi Yuan, Ziang Xiao, Prithviraj Ammanabrolu, Marc-Alexandre Côté

机构 * University of California, San Diego（加州大学圣迭戈分校） ； Microsoft Research Montréal（微软研究院蒙特利尔分部） ； Johns Hopkins University（约翰霍普金斯大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions

Emre Can Acikgoz, Cheng Qian, Hongru Wang, Vardhan Dongre, Xiusi Chen, Heng Ji, Dilek Hakkani-Tür, Gokhan Tur

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities

Thomas Schmied, Jörg Bornschein, Jordi Grau-Moya, Markus Wulfmeier, Razvan Pascanu

机构 * ELLIS Unit, LIT AI Lab, Institute for Machine Learning, JKU Linz（ELLIS单元、LIT人工智能实验室、机器学习研究所、JKU林茨） ； Google DeepMind（谷歌DeepMind） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

PolicyEvol-Agent: Evolving Policy via Environment Perception and Self-Awareness with Theory of Mind

Yajie Yu, Yue Feng

机构 * School of Computer Science University of Birmingham（计算机科学学院 英国伯明翰大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Seek and Solve Reasoning for Table Question Answering

Ruya Jiang, Chun Wang, Weihong Deng

机构 * nd University of Toronto（多伦多大学） ； st Mashang Consumer Finance Co., Ltd.（马莎消费金融有限公司） ； Mashang Consumer Finance Co., Ltd.（马莎消费金融有限公司） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Published in: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural Integration

Yicheng Pan, Zhenrong Zhang, Pengfei Hu, Jiefeng Ma, Jun Du, Jianshu Zhang, Quan Liu, Jianqing Gao, Feng Ma

机构 * University of Science and Technology of China（中国科学技术大学） ； iFLYTEK Research（讯飞研究院） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments 10 pages, 5 figures

Generating Planning Feedback for Open-Ended Programming Exercises with LLMs

Mehmet Arif Demirtaş, Claire Zheng, Max Fowler, Kathryn Cunningham

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted as full paper at AIED 2025

Orchestrating Agents and Data for Enterprise: A Blueprint Architecture for Compound AI

Eser Kandogan, Nikita Bhutani, Dan Zhang, Rafael Li Chen, Sairam Gurajada, Estevam Hruschka

机构 * Megagon Labs（美格根实验室） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Journal ref First Workshop on Data-AI Systems (DAIS), ICDE 2025

NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization

Md Mahadi Hasan Nahid, Davood Rafiei

机构 * University of Alberta（阿尔伯塔大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments EMNLP 2024 (Findings)

Contradiction Detection in RAG Systems: Evaluating LLMs as Context Validators for Improved Information Consistency

Vignesh Gokul, Srikanth Tenneti, Alwarappan Nakkiran

机构 * Amazon（亚马逊公司） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL

Mohammadreza Pourreza, Shayan Talaei, Ruoxi Sun, Xingchen Wan, Hailong Li, Azalia Mirhoseini, Amin Saberi, Sercan "O. Arik

机构 * Google Cloud（谷歌云） ； Stanford University（斯坦福大学） ； Google DeepMind（谷歌DeepMind） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；SFT(abstract)；分类 cs.AI、cs.LG

Comments Mohammadreza Pourreza and Shayan Talaei contributed equally to this work