大模型推理能力

Optimizing Chain-of-Thought Confidence via Topological and Dirichlet Risk Analysis

Abhishek More, Anthony Zhang, Nicole Bonilla, Ashvik Vivekan, Kevin Zhu, Parham Sharafoleslami, Maheep Chaudhary

机构 * Algoverse AI Research（Algoverse AI研究院） 纠错

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

What Makes Reasoning Invalid: Echo Reflection Mitigation for Large Language Models

Chen He, Xun Jiang, Lei Wang, Hao Yang, Chong Peng, Peng Yan, Fumin Shen, Xing Xu

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

Kunlun Anomaly Troubleshooter: Enabling Kernel-Level Anomaly Detection and Causal Reasoning for Large Model Distributed Inference

Yuyang Liu, Jingjing Cai, Jiayi Ren, Peng Zhou, Danyang Zhang, Yin Du, Shijian Li

机构 * Alibaba Group（阿里巴巴集团） 纠错

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

Comments Preprint version, under submission

SMAGDi: Socratic Multi Agent Interaction Graph Distillation for Efficient High Accuracy Reasoning

Aayush Aluru, Myra Malik, Samarth Patankar, Spencer Kim, Kevin Zhu, Sean O'Brien, Vasu Sharma

机构 * Algoverse AI Research（Algoverse AI研究） 纠错

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

Comments Multi-Turn Interactions in Large Language Models (MTI-LLM) Workshop at NeurIPS 2025

Collaborative LLM Numerical Reasoning with Local Data Protection

Min Zhang, Yuzhe Lu, Yun Zhou, Panpan Xu, Lin Lee Cheong, Chang-Tien Lu, Haozhu Wang

机构 * AWS AI（AWS人工智能） 纠错

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

Comments Accepted to AAAI-2026

Self-Evaluating LLMs for Multi-Step Tasks: Stepwise Confidence Estimation for Failure Detection

Vaibhav Mavi, Shubh Jaroria, Weiqi Sun

机构 * Dyania Health（Dyania健康） 纠错

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

Comments Accepted at NeurIPS 2025 Workshop on Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling

TuckA: Hierarchical Compact Tensor Experts for Efficient Fine-Tuning

Qifeng Lei, Zhiyong Yang, Qianqian Xu, Cong Hua, Peisong Wen, Qingming Huang

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

Data Trajectory Alignment for LLM Domain Adaptation: A Two-Phase Synthesis Framework for Telecommunications Mathematics

Zhicheng Zhou, Jing Li, Suming Qiu, Junjie Huang, Linyuan Qiu, Zhijie Sun

机构 * Global Technical Service (GTS) Huawei Technologies Co., Ltd（华为技术有限公司全球技术服务部） 纠错

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

Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch

Yirong Zeng, Xiao Ding, Yutai Hou, Yuxian Wang, Li Du, Juyi Dai, Qiuyang Ding, Duyu Tang, Dandan Tu, Weiwen Liu, Bing Qin, Ting Liu

机构 * Harbin Institute of Technology SCIR Lab（哈尔滨工业大学SCIR实验室） ； Huawei Technologies Co., Ltd（华为技术有限公司） ； Shanghai Jiao Tong University（上海交通大学） ； Beijing Academy of Artificial Intelligence（北京人工智能研究院） 纠错

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

Comments EMNLP 2025 finding

Towards Conversational AI for Human-Machine Collaborative MLOps

George Fatouros, Georgios Makridis, George Kousiouris, John Soldatos, Anargyros Tsadimas, Dimosthenis Kyriazis

机构 * Innov-Acts Ltd（Innov-Acts公司） ； Dept. of Digital Systems（数字系统系） ； University of Piraeus（比雷埃克斯大学） ； Dept. of Informatics and Telematics（信息与电信学系） ； Harokopio University（哈罗科比奥大学） 纠错

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

Comments 8 pages, 5 figures

Journal ref 2025 21st International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT)

TimeSense:Making Large Language Models Proficient in Time-Series Analysis

Zhirui Zhang, Changhua Pei, Tianyi Gao, Zhe Xie, Yibo Hao, Zhaoyang Yu, Longlong Xu, Tong Xiao, Jing Han, Dan Pei

机构 * Tsinghua University（清华大学） ； Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心） ； ZTE Corporation（中兴通讯） 纠错

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

Zooming into Comics: Region-Aware RL Improves Fine-Grained Comic Understanding in Vision-Language Models

Yule Chen, Yufan Ren, Sabine Süsstrunk

机构 * School of Computer and Communication Sciences, EPFL（瑞士联邦理工学院计算机与通信科学学院） ； Department of Computer Science and Engineering, Chalmers University of Technology（楚科奇技术大学计算机科学与工程系） ； IVRL, EPFL（EPFL智能机器人实验室） 纠错

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

Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinement

Hiroaki Hayashi, Bo Pang, Wenting Zhao, Ye Liu, Akash Gokul, Srijan Bansal, Caiming Xiong, Semih Yavuz, Yingbo Zhou

机构 * Salesforce AI Research（Salesforce人工智能研究） 纠错

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

GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining

Chunyu Wei, Wenji Hu, Xingjia Hao, Xin Wang, Yifan Yang, Yueguo Chen, Yang Tian, Yunhai Wang

机构 * Renmin University of China（中国人民大学） ； Guangxi University（广西大学） ； Beijing Jiaotong University（北京交通大学） 纠错

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

Comments Accepted by NeurIPS 2025

LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora

Luyao Zhuang, Shengyuan Chen, Yilin Xiao, Huachi Zhou, Yujing Zhang, Hao Chen, Qinggang Zhang, Xiao Huang

机构 * The Department of Computing, Hong Kong Polytechnic University, Hong Kong SAR（香港理工大学计算机系） 纠错

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

Large model retrieval enhancement framework for construction site risk identification

Jiawei Li, Chengye Yang, Yaochen Zhang, Weilin Sun, Lei Meng, Xiangxu Meng

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

Comments in Chinese language

AesTest: Measuring Aesthetic Intelligence from Perception to Production

Guolong Wang, Heng Huang, Zhiqiang Zhang, Wentian Li, Feilong Ma, Xin Jin

机构 * University of International Business and Economics（国际商务经济大学） ； University of Science and Technology of China（中国科学技术大学） ； Huawei Technologies Co., Ltd（华为技术有限公司） ； Beijing Electronic Science and Technology Institute（北京电子科技研究所） ； Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

Comments 10 pages, 9 figures

Gentle Manipulation Policy Learning via Demonstrations from VLM Planned Atomic Skills

Jiayu Zhou, Qiwei Wu, Jian Li, Zhe Chen, Xiaogang Xiong, Renjing Xu

专题命中 复杂问题求解 ：planning(abstract)

Comments Accepted for the 40th Annual AAAI Conference on Artificial Intelligence (2026)

Vector-Quantized Vision Foundation Models for Object-Centric Learning

Rongzhen Zhao, Vivienne Wang, Juho Kannala, Joni Pajarinen

机构 * Aalto University（阿alto大学） ； University of Oulu（奥卢大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

Comments Accepted to ACM MM 2025