机构
*
School of Computer Science and Technology, Beijing Institute of Technology, China(北京理工大学计算机科学与技术学院)
;
School of Computer Science and Technology, Huazhong University of Science and Technology, China(华中科技大学计算机科学与技术学院)
;
Independent, China(独立)
Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts
思想检索:通过重用思想实现高效推理
Ammar Ahmed, Azal Ahmad Khan, Ayaan Ahmad, Sheng Di, Zirui Liu, Ali Anwar
机构
*
Department of Computer Science and Engineering, University of Minnesota(明尼苏达大学计算机科学与工程系)
;
Department of Computer Science and Engineering, University of California Santa Cruz(加州大学圣克鲁兹分校计算机科学与工程系)
;
Argonne National Laboratory(阿贡国家实验室)
Weak-Link Optimization for Multi-Agent Reasoning and Collaboration
多智能体推理与协作中的弱链接优化
Haoyu Bian, Chaoning Zhang, Jiaquan Zhang, Xingyao Li, Yuanfang Guo, Wei Dong, Yang Yang
机构
*
University of Electronic Science and Technology of China(电子科技大学)
;
Beihang University(北航)
;
Xi'an University of Architecture and Technology(西安建筑科技大学)
Dissecting Failure Dynamics in Large Language Model Reasoning
解析大语言模型推理中的故障动态
Wei Zhu, Jian Zhang, Lixing Yu, Kun Yue, Zhiwen Tang
机构
*
School of Information Science and Engineering, Yunnan University, Kunming, China(云南大学信息科学与工程学院,昆明,中国)
;
Yunnan Key Laboratory of Intelligent Systems and Computing, Kunming, China(云南省智能系统与计算重点实验室,昆明,中国)
Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model
深度对齐但不确定性依然存在:通过将不安全行为归因于基础模型来改进推理时间的安全性
Pankayaraj Pathmanathan, Furong Huang
机构
*
University of Maryland College Park(马里兰大学学院市)
From Prediction to Justification: Aligning Sentiment Reasoning with Human Rationale via Reinforcement Learning
从预测到论证:通过强化学习对齐情感推理与人类推理
Shihao Zhang, Ziwei Wang, Jie Zhou, Yulan Wu, Qin Chen, Zhikai Lei, Liyang Yu, Liang Dou, Liang He
机构
*
School of Computer Science and Technology, East China Normal University(东华大学计算机科学与技术学院)
;
Shanghai Qiji Zhifeng Co., Ltd.(上海启智丰科技有限公司)
;
Ocean University of China(中国海洋大学)
FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models
FoE:错误森林使大推理模型中的首个解成为最佳解
Kehan Jiang, Haonan Dong, Zhaolu Kang, Zhengzhou Zhu, Guojie Song
机构
*
School of Software and Microelectronics, Peking University(北京大学软件与微电子学院)
;
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学院通用人工智能国家重点实验室)
Think Twice Before You Write -- an Entropy-based Decoding Strategy to Enhance LLM Reasoning
再三思考后再写作——一种基于熵的解码策略以增强大语言模型推理
Jiashu He, Meizhu Liu, Olaitan P Olaleye, Amit Agarwal, M. Avendi, Yassi Abbasi, Matthew Rowe, Hitesh Laxmichand Patel, Paul Li, Tao Sheng, Sujith Ravi, Dan Roth
机构
*
Oracle AI Science(甲骨文人工智能科学)
;
University of Pennsylvania(宾夕法尼亚大学)
GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler
GTS:基于可学习高斯思维采样器的推理时缩放
Minghan Wang, Ye Bai, Thuy-Trang Vu, Ehsan Shareghi, Gholamreza Haffari
机构
*
Department of Data Science & AI, Monash University(墨尔本大学数据科学与人工智能系)
;
Faculty of Medicine Dentistry and Health Sciences, University of Melbourne(墨尔本大学医学牙科与健康科学学院)
;
Department of Computer Science, University College London(伦敦大学学院计算机科学系)
Zhibin Lan, Liqiang Niu, Fandong Meng, Jie Zhou, Jinsong Su
机构
*
School of Informatics, Xiamen University, China(厦门大学信息学院)
;
WeChat AI, Tencent Inc, China(腾讯公司微信AI部门)
;
Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism, China(福建省和台湾非物质文化遗产数字化保护与智能处理重点实验室)
;
Shanghai Artificial Intelligence Laboratory, China(上海人工智能实验室)