大模型推理能力

SilVar: Speech Driven Multimodal Model for Reasoning Visual Question Answering and Object Localization

Tan-Hanh Pham, Hoang-Nam Le, Phu-Vinh Nguyen, Chris Ngo, Truong-Son Hy

专题命中 复杂问题求解 ：reasoning(title,abstract)；CoT(abstract)

Comments 10 pages

Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models

Shayekh Bin Islam, Md Asib Rahman, K S M Tozammel Hossain, Enamul Hoque, Shafiq Joty, Md Rizwan Parvez

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to EMNLP 2024 Findings. Website: https://openragmoe.github.io/. 14 pages, 7 figures, 5 tables

On The Role of Reasoning in the Identification of Subtle Stereotypes in Natural Language

Jacob-Junqi Tian, Omkar Dige, D. B. Emerson, Faiza Khan Khattak

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 15 pages, 11 Figures, 3 Tables

ExoViP: Step-by-step Verification and Exploration with Exoskeleton Modules for Compositional Visual Reasoning

Yuxuan Wang, Alan Yuille, Zhuowan Li, Zilong Zheng

专题命中 复杂问题求解 ：reasoning(title,abstract)；planning(abstract)

Comments To Appear at COLM 2024

CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples

Jianrui Zhang, Mu Cai, Tengyang Xie, Yong Jae Lee

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 15 pages, 6 figures, 12 tables, Project Page: https://countercurate.github.io/

Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning

Joongwon Kim, Bhargavi Paranjape, Tushar Khot, Hannaneh Hajishirzi

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 50 pages, 42 figures. Project webpage available [here](https://agent-husky.github.io/)

Towards LLM-Powered Verilog RTL Assistant: Self-Verification and Self-Correction

Hanxian Huang, Zhenghan Lin, Zixuan Wang, Xin Chen, Ke Ding, Jishen Zhao

专题命中 复杂问题求解 ：self-correction(title)；reasoning(abstract)；chain-of-thought(abstract)

GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning

Costas Mavromatis, George Karypis

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

MMCTAgent: Multi-modal Critical Thinking Agent Framework for Complex Visual Reasoning

Somnath Kumar, Yash Gadhia, Tanuja Ganu, Akshay Nambi

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Case-Based Reasoning Approach for Solving Financial Question Answering

Yikyung Kim, Jay-Yoon Lee

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

ADaPT: As-Needed Decomposition and Planning with Language Models

Archiki Prasad, Alexander Koller, Mareike Hartmann, Peter Clark, Ashish Sabharwal, Mohit Bansal, Tushar Khot

专题命中 复杂问题求解 ：planning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments NAACL 2024 (findings) camera-ready. Project Page: https://allenai.github.io/adaptllm

Deja vu: Contrastive Historical Modeling with Prefix-tuning for Temporal Knowledge Graph Reasoning

Miao Peng, Ben Liu, Wenjie Xu, Zihao Jiang, Jiahui Zhu, Min Peng

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to NAACL 2024 Findings

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

Zhiheng Xi, Wenxiang Chen, Boyang Hong, Senjie Jin, Rui Zheng, Wei He, Yiwen Ding, Shichun Liu, Xin Guo, Junzhe Wang, Honglin Guo, Wei Shen, Xiaoran Fan, Yuhao Zhou, Shihan Dou, Xiao Wang, Xinbo Zhang, Peng Sun, Tao Gui, Qi Zhang, Xuanjing Huang

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Preprint. Codes released: https://github.com/WooooDyy/LLM-Reverse-Curriculum-RL

Laying the Foundation First? Investigating the Generalization from Atomic Skills to Complex Reasoning Tasks

Yuncheng Huang, Qianyu He, Yipei Xu, Jiaqing Liang, Yanghua Xiao

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Reasoning with Language Model Prompting: A Survey

Shuofei Qiao, Yixin Ou, Ningyu Zhang, Xiang Chen, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, Huajun Chen

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ACL 2023, 24 pages, add references of theoretical analysis

External Reasoning: Towards Multi-Large-Language-Models Interchangeable Assistance with Human Feedback

Akide Liu

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments technical report, add code link. arXiv admin note: text overlap with arXiv:2305.11206 by other authors

Entity Alignment with Reliable Path Reasoning and Relation-Aware Heterogeneous Graph Transformer

Weishan Cai, Wenjun Ma, Jieyu Zhan, Yuncheng Jiang

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted by IJCAI-ECAI 2022

Hypergraph Transformer: Weakly-supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering

Yu-Jung Heo, Eun-Sol Kim, Woo Suk Choi, Byoung-Tak Zhang

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted at ACL 2022

TempoQR: Temporal Question Reasoning over Knowledge Graphs

Costas Mavromatis, Prasanna Lakkur Subramanyam, Vassilis N. Ioannidis, Soji Adeshina, Phillip R. Howard, Tetiana Grinberg, Nagib Hakim, George Karypis

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments AAAI 2022

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

Rui Wang, Hongru Wang, Boyang Xue, Jianhui Pang, Shudong Liu, Yi Chen, Jiahao Qiu, Derek Fai Wong, Heng Ji, Kam-Fai Wong

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments In Progress; Paper list Repo: https://github.com/DevoAllen/Awesome-Reasoning-Economy-Papers

Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios

Shantanu Jaiswal, Debaditya Roy, Basura Fernando, Cheston Tan

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.AI、cs.LG

Comments NeurIPS 2024 camera ready; source code to be released at: https://github.com/shantanuj/IPRM_Iterative_and_Parallel_Reasoning_Mechanism

Hierarchical Deconstruction of LLM Reasoning: A Graph-Based Framework for Analyzing Knowledge Utilization

Miyoung Ko, Sue Hyun Park, Joonsuk Park, Minjoon Seo

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments published at EMNLP 2024; code is available at https://github.com/kaistAI/knowledge-reasoning

LexKairos: Benchmarking Legal Temporal Capabilities in LLMs

LexKairos：评估大型语言模型的法律时间能力基准

Chenyang Li, Zejia Feng, Yuqin Huang, Yuxiao Ye, Huiyuan Xie

专题命中 复杂问题求解 ：CoT(abstract,abstract_cn)；reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

AI总结 本研究提出LexKairos基准，评估LLMs的中文法律时间能力，经多设置测试发现Gemini-3-Flash表现最优，但现有模型在时间敏感任务上仍存局限，相关能力待提升。

Comments 15 pages, 5 figures

Conformity Mitigations in Large Language Models Lie on a Single Resistance-Receptivity Frontier

大语言模型中的从众效应缓解措施存在于单一的抵抗-接受边界上

Zafar Hussain, Kristoffer Nielbo

机构 * Aarhus University（奥胡斯大学） 纠错

专题命中 复杂问题求解 ：reasoning(summary_cn,abstract)；分类 cs.AI

AI总结 该研究针对大语言模型的从众效应，提出抵抗-接受双维度评估，发现多数缓解措施存在此消彼长的边界，仅Reasoning可同时提升抵抗性与接受性。

VideoLatent: Video-Language Learning via Latent Self-Forcing

VideoLatent: 通过潜在自强制进行视频-语言学习

Zi-Yuan Hu, Zicong Tang, Shijia Huang, Yanyang Li, Michael R. Lyu, Liwei Wang

机构 * The Chinese University of Hong Kong（香港中文大学） ； Weitu AI（微图AI） 纠错

专题命中 复杂问题求解 ：CoT(abstract,abstract_cn)；reasoning(abstract)；chain-of-thought(abstract)；分类 cs.AI

AI总结 提出VideoLatent，一种通过潜在自强制训练范式（包括潜在对齐和潜在多样性目标）进行视觉潜在推理的多模态大语言模型，仅依赖标准视频-问答三元组，在14个基准上优于现有模型，并大幅降低训练/推理开销。

MA$^{2}$P: A Meta-Cognitive Autonomous Intelligent Agents Framework for Complex Persuasion

MA$^{2}$P: 一种用于复杂说服的元认知自主智能体框架

Dingyi Zhang, Ziqing Zhuang, Linhai Zhang, Ziyang Gao, Deyu Zhou

机构 * School of Computer Science and Engineering, Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University, China（计算机科学与工程学院、计算机网络与信息集成重点实验室、教育部、东南大学，中国） ； Department of Informatics, King’s College London（信息学院、伦敦国王学院） 纠错

专题命中 复杂问题求解 ：reasoning(abstract,abstract_cn)；planning(abstract,abstract_cn)；分类 cs.CL

AI总结 本文提出MA$^{2}$P框架，通过自主多智能体架构和元认知配置器，解决复杂说服中说服者需解读内部状态、推断潜在心理状态并生成策略一致行动的挑战，提升说服成功率。

Comments 22 pages, 8 figures. Accepted to Findings of ACL 2026

ACIL: Auto Chain of Thoughts for In-Context Learning

ACIL: 自动链式思维用于上下文学习

Rui Chu

机构 * Rui Chu（楚瑞） 纠错

专题命中 复杂问题求解 ：CoT(abstract,abstract_cn)；reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

AI总结 本文提出ACIL框架，通过自动构建包含推理步骤的演示来提升上下文学习在多步推理任务中的性能。

CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding

CGC：基于组成性 grounded 对比的细粒度多图像理解

Lihao Zheng, Zhenwei Shao, Yu Zhou, Yan Yang, Xintian Shen, Jiawei Chen, Hao Ma, Tao Wei

机构 * School of Computer Science and Technology, Hangzhou Dianzi University（杭州电子科技大学计算机科学与技术学院） ； School of Computer Science（计算机科学学院） ； Technology, Hangzhou Dianzi University（技术，杭州电子科技大学） 纠错

专题命中 复杂问题求解 ：CoT(abstract,abstract_cn)；reasoning(abstract)；chain-of-thought(abstract)；分类 cs.AI

AI总结 本文提出CGC框架，通过跨图像对比和内图像对比提升多图像细粒度理解，结合规则空间奖励增强属性和对齐，实验显示在多个基准上取得最佳结果，并在多模态任务中表现优异。

Evolutionary Prompt Optimization Discovers Emergent Multimodal Reasoning Strategies in Vision-Language Models

Sid Bharthulwar, John Rho, Katrina Brown

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL；planning(comments)

Comments Published at ICLR 2025 Workshop on Reasoning and Planning for LLMs

Reasoning Effort and Problem Complexity: A Scaling Analysis in LLMs

Benjamin Estermann, Roger Wattenhofer

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.AI；planning(comments)

Comments Published at ICLR 2025 Workshop on Reasoning and Planning for LLMs