大模型推理能力

MasonTigers at SemEval-2024 Task 9: Solving Puzzles with an Ensemble of Chain-of-Thoughts

Md Nishat Raihan, Dhiman Goswami, Al Nahian Bin Emran, Sadiya Sayara Chowdhury Puspo, Amrita Ganguly, Marcos Zampieri

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

ESG Classification by Implicit Rule Learning via GPT-4

Hyo Jeong Yun, Chanyoung Kim, Moonjeong Hahm, Kyuri Kim, Guijin Son

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

Comments Accepted as Shared Track Paper at 7th FinNLP Workshop @ LREC-COLING 2024

Dr3: Ask Large Language Models Not to Give Off-Topic Answers in Open Domain Multi-Hop Question Answering

Yuan Gao, Yiheng Zhu, Yuanbin Cao, Yinzhi Zhou, Zhen Wu, Yujie Chen, Shenglan Wu, Haoyuan Hu, Xinyu Dai

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

Comments LREC-COLING 2024, Long Paper

Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Study

Yaxin Fan, Feng Jiang, Peifeng Li, Haizhou Li

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

Comments Accepted by LREC-COLING'2024

AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System

Zhiwei Liu, Weiran Yao, Jianguo Zhang, Liangwei Yang, Zuxin Liu, Juntao Tan, Prafulla K. Choubey, Tian Lan, Jason Wu, Huan Wang, Shelby Heinecke, Caiming Xiong, Silvio Savarese

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

Comments preprint. Library is available at https://github.com/SalesforceAIResearch/AgentLite

Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models

Xuanyu Lei, Zonghan Yang, Xinrui Chen, Peng Li, Yang Liu

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

Understanding the Weakness of Large Language Model Agents within a Complex Android Environment

Mingzhe Xing, Rongkai Zhang, Hui Xue, Qi Chen, Fan Yang, Zhen Xiao

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

Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings

Daniel Rose, Vaishnavi Himakunthala, Andy Ouyang, Ryan He, Alex Mei, Yujie Lu, Michael Saxon, Chinmay Sonar, Diba Mirza, William Yang Wang

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

DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendation

Yu Wang, Zhiwei Liu, Jianguo Zhang, Weiran Yao, Shelby Heinecke, Philip S. Yu

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

Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication

Zhangyue Yin, Qiushi Sun, Cheng Chang, Qipeng Guo, Junqi Dai, Xuanjing Huang, Xipeng Qiu

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

Comments 19 pages, 11 figures, accepted by EMNLP2023

A Zero-Shot Language Agent for Computer Control with Structured Reflection

Tao Li, Gang Li, Zhiwei Deng, Bryan Wang, Yang Li

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

Comments Accepted at Findings of EMNLP 2023

NQE: N-ary Query Embedding for Complex Query Answering over Hyper-Relational Knowledge Graphs

Haoran Luo, Haihong E, Yuhao Yang, Gengxian Zhou, Yikai Guo, Tianyu Yao, Zichen Tang, Xueyuan Lin, Kaiyang Wan

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

Comments Accepted by AAAI 2023

Journal ref AAAI 2023

Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners

Allen Z. Ren, Anushri Dixit, Alexandra Bodrova, Sumeet Singh, Stephen Tu, Noah Brown, Peng Xu, Leila Takayama, Fei Xia, Jake Varley, Zhenjia Xu, Dorsa Sadigh, Andy Zeng, Anirudha Majumdar

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

Comments Conference on Robot Learning (CoRL) 2023, Oral Presentation

TaskLAMA: Probing the Complex Task Understanding of Language Models

Quan Yuan, Mehran Kazemi, Xin Xu, Isaac Noble, Vaiva Imbrasaite, Deepak Ramachandran

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

Chain of Thought Prompt Tuning in Vision Language Models

Jiaxin Ge, Hongyin Luo, Siyuan Qian, Yulu Gan, Jie Fu, Shanghang Zhang

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

PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents

Simeng Sun, Yang Liu, Shuohang Wang, Chenguang Zhu, Mohit Iyyer

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

How Many Demonstrations Do You Need for In-context Learning?

Jiuhai Chen, Lichang Chen, Chen Zhu, Tianyi Zhou

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

Repurposing of Resources: from Everyday Problem Solving through to Crisis Management

Antonis Bikakis, Luke Dickens, Anthony Hunter, Rob Miller

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

Comments 16 pages

Toward More Reliable Artificial Intelligence: Reducing Hallucinations in Vision-Language Models

迈向更可靠的人工智能：减少视觉-语言模型中的幻觉

Kassoum Sanogo, Renzo Ardiccioni

机构 * Department of CS AI and Data Science（计算机科学与数据科学系） ； ESEO Engineering School（ESEO工程学院） ； Faculty of Law, Economy, Management（法学院、经济与管理学院） 纠错

专题命中 复杂问题求解 ：self-correction(abstract,comments)；分类 cs.CL、cs.AI、cs.LG

AI总结 本文提出无需训练的自我纠正框架，通过不确定性引导的视觉再注意力减少视觉-语言模型中的幻觉，提升响应准确性。

Comments 24 pages, 3 figures, 2 tables. Training-free self-correction framework for vision-language models. Code and implementation details will be released at: https://github.com/kassoumsanogo1/self-correcting-vlm-re-Attention.git

Journal ref The 4th National and International Academic Conference Celebrating the 20th Anniversary of Rajapruk University (2026)

DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents

DART-SD：面向多轮工具调用智能体自蒸馏的钻石拓扑感知检索与微调

Hangrui Xu, Jiarui Wang, Yang Yang, Chuanbo Zhu, Fangda Chen, Ziqi Wu, Jingming Cai, Yan Song

机构 * ByteDance（字节跳动） ； University of Science and Technology of China（中国科学技术大学） 纠错

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

AI总结 本文针对多轮工具调用智能体训练中的拓扑崩溃问题，提出DART-SD框架，通过建模拓扑、检索恢复参考与渐进自蒸馏提升策略多样性，性能优于传统全轨迹基线。

Agentic Transaction: Towards ACID-Compliant Agent Systems

智能体事务：面向ACID兼容的智能体系统

Zhaoyan Sun, Xiaoxiao Wang, Guoliang Li

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

AI总结 该研究提出ACID兼容的智能体事务框架，开发对应数据智能体，在基准测试中较含Claude Code的现有智能体提升10.6%，为构建可信可扩展AI智能体开辟新方向。

TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

TraceSafe: 对LLM在多步骤工具调用轨迹上的安全护栏的系统评估

Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang, Yun-Nung Chen

机构 * CyCraft AI Lab, Taiwan（CyCraft AI实验室（台湾）） ； National Taiwan University（国立台湾大学） 纠错

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

AI总结 本文提出TraceSafe-Bench，首个评估中间轨迹安全的综合基准，发现安全护栏效果更依赖结构数据能力而非语义安全对齐，通用模型在轨迹分析中表现更优，且准确性随执行步骤增加而提升。

Comments Accepted to Conference on Language Modeling (COLM) 2026

Kimi K2.5: Visual Agentic Intelligence

Kimi K2.5：视觉代理智能

Kimi Team, Tongtong Bai, Yifan Bai, Yiping Bao, S. H. Cai, Yuan Cao, Ziwei Chai, Y. Charles, H. S. Che, Cheng Chen, Guanduo Chen, Huarong Chen, Jia Chen, Jianlong Chen, Jun Chen, Kefan Chen, Liang Chen, Ruijue Chen, Xinhao Chen, Yanru Chen, Yanxu Chen, Yicun Chen, Yimin Chen, Yingjiang Chen, Yuankun Chen, Yujie Chen, Yutian Chen, Zhirong Chen, Ziwei Chen, Dazhi Cheng, Yean Cheng, Minghan Chu, Jialei Cui, Jiaqi Deng, Muxi Diao, Hao Ding, Mengfan Dong, Mengnan Dong, Yuxin Dong, Yuhao Dong, Angang Du, Chenzhuang Du, Dikang Du, Lingxiao Du, Yulun Du, Yu Fan, Shengjun Fang, Qiulin Feng, Yichen Feng, Garimugai Fu, Kelin Fu, Hongcheng Gao, Tong Gao, Yuyao Ge, Shangyi Geng, Chengyang Gong, Xiaochen Gong, Zhuoma Gongque, Qizheng Gu, Xinran Gu, Yicheng Gu, Longyu Guan, Shuhao Guan, Yuanying Guo, Xiaoru Hao, Dailan He, Tianhong He, Weiran He, Wenyang He, Yibo He, Yunjia He, Chao Hong, Hao Hu, Jiaxi Hu, Yangyang Hu, Zhenxing Hu, Ke Huang, Ruiyuan Huang, Weixiao Huang, Zhiqi Huang, Chaobo Jia, Tao Jiang, Zhejun Jiang, Xinyi Jin, Yu Jing, Guokun Lai, Aidi Li, C. Li, Cheng Li, Fang Li, Guanghe Li, Guanyu Li, Haitao Li, Haoyang Li, Jia Li, Jingwei Li, Junxiong Li, Lincan Li, Mo Li, Weihong Li, Wentao Li, Xinhang Li, Xinhao Li, Yang Li, Yanhao Li, Yiwei Li, Yuxiao Li, Zhaowei Li, Zhaoxi Li, Zheming Li, Weilong Liao, Jiawei Lin, Xiaohan Lin, Yibo Lin, Zhishan Lin, Zichao Lin, Cheng Liu, Chenyu Liu, Hongzhang Liu, Liang Liu, Shaowei Liu, Shudong Liu, Shuran Liu, Tianwei Liu, Tianyu Liu, Weizhou Liu, Xiangyan Liu, Yangyang Liu, Yanming Liu, Yibo Liu, Yuanxin Liu, Zhengying Liu, Zhongnuo Liu, Enzhe Lu, Haoyu Lu, Zhiyuan Lu, G. Luo, Junyu Luo, Tongxu Luo, Yashuo Luo, Long Ma, Shaoguang Mao, Yuan Mei, Xin Men, Fanqing Meng, Zhiyong Meng, Yibo Miao, Minqing Ni, Kun Ouyang, Siyuan Pan, Bo Pang, Yuchao Qian, Ruoyu Qin, Zeyu Qin, Jiezhong Qiu, Bowen Qu, Zeyu Shang, Youbo Shao, Tianxiao Shen, Zhennan Shen, Juanfeng Shi, Lidong Shi, Shengyuan Shi, Feifan Song, Pengwei Song, Tianhui Song, Xiaoxi Song, Hongjin Su, Jianlin Su, Zhaochen Su, Lin Sui, Jinsong Sun, Junyao Sun, Tongyu Sun, Flood Sung, Yunpeng Tai, Chuning Tang, Heyi Tang, Xiaojuan Tang, Zhengyang Tang, Jiawen Tao, Shiyuan Teng, Chaoran Tian, Pengfei Tian, Bowen Wang, Chensi Wang, Chuang Wang, Congcong Wang, Dingkun Wang, Dinglu Wang, Dongliang Wang, Feng Wang, Hailong Wang, Haiming Wang, Hao Wang, Hengzhi Wang, Huaqing Wang, Hui Wang, Jiahao Wang, Jinhong Wang, Jiuzheng Wang, Kaixin Wang, Linian Wang, Qibin Wang, Shengjie Wang, Shuyi Wang, Si Wang, Wei Wang, Xiaochen Wang, Xinyuan Wang, Yao Wang, Yejie Wang, Yipu Wang, Yiqin Wang, Yucheng Wang, Yuzhi Wang, Zhaoji Wang, Zhaowei Wang, Zhengtao Wang, Zhexu Wang, Zifan Wang, Zihan Wang, Zizhe Wang, Chu Wei, Ming Wei, Chuan Wen, Zichen Wen, Chengjie Wu, Haoning Wu, Junyan Wu, Rucong Wu, Wenhao Wu, Yuefeng Wu, Yuhao Wu, Yuxin Wu, Zijian Wu, Chenjun Xiao, Jin Xie, Xiaotong Xie, Yuchong Xie, Bowei Xing, Boyu Xu, Jianfan Xu, Jing Xu, Jinjing Xu, L. H. Xu, Lin Xu, Suting Xu, Weixin Xu, Xinbo Xu, Xinran Xu, Yangchuan Xu, Yichang Xu, Yuemeng Xu, Zelai Xu, Ziyao Xu, Junjie Yan, Yuzi Yan, Guangyao Yang, Hao Yang, Junwei Yang, Kai Yang, Ningyuan Yang, Xiaofei Yang, Xinlong Yang, Xinyu Yang, Ying Yang, Yi Yang, Yi Yang, Zhen Yang, Zhilin Yang, Zonghan Yang, Haotian Yao, Dan Ye, Haoran Ye, Wenjie Ye, Zhuorui Ye, Peng Yebo, Bohong Yin, Chengzhen Yu, Longhui Yu, Tao Yu, Tianxiang Yu, Enming Yuan, Mengjie Yuan, Xiaokun Yuan, Yang Yue, Weihao Zeng, Dunyuan Zha, Haobing Zhan, Dehao Zhang, Hao Zhang, Jin Zhang, Puqi Zhang, Qiao Zhang, Rui Zhang, Xiaobin Zhang, Xiaoyun Zhang, Y. Zhang, Yadong Zhang, Yangkun Zhang, Yichi Zhang, Yizhi Zhang, Yongting Zhang, Yu Zhang, Yushun Zhang, Yutao Zhang, Yutong Zhang, Zheng Zhang, Chenguang Zhao, Feifan Zhao, Jinxiang Zhao, Shuai Zhao, Xiangyu Zhao, Xuanle Zhao, Yikai Zhao, Zijia Zhao, Huabin Zheng, Ruihan Zheng, Shaojie Zheng, Tengyang Zheng, Junfeng Zhong, Longguang Zhong, Weiming Zhong, M. Zhou, Runjie Zhou, Xinyu Zhou, Zaida Zhou, Jinguo Zhu, Liya Zhu, Xinhao Zhu, Yuxuan Zhu, Zhen Zhu, Jingze Zhuang, Weiyu Zhuang, Ying Zou, Xinxing Zu

机构 * Kimi Team（Kimi 团队） 纠错

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

AI总结 Kimi K2.5通过联合优化文本和视觉模态，提出Agent Swarm框架，实现多模态代理智能的先进性能和高效任务处理。

Comments Kimi K2.5 tech report

DeepImagine: Clinical Trial Outcome Prediction via Stepwise Local Counterfactual Imaginations

DeepImagine: 通过连续反事实想象学习生物医学推理

Youze Zheng, Jianyou Wang, Yuhan Chen, Matthew Feng, Longtian Bao, Hanyuan Zhang, Maxim Khan, Aditya K. Sehgal, Christopher D. Rosin, Umber Dube, Ramamohan Paturi

机构 * Laboratory for Emerging Intelligence, University of California, San Diego（新兴智能实验室，加州大学圣地亚哥分校） ； Department of Dermatology, University of California, San Diego（皮肤科系，加州大学圣地亚哥分校） ； University of Chicago（芝加哥大学） ； Elsevier（艾尔斯特出版社） 纠错

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

AI总结 本文提出DeepImagine框架，通过连续反事实想象训练语言模型进行生物医学推理，利用反事实对偶和强化学习提升临床试验预测性能，展示模型在生物医学领域的可解释性改进。

Comments Preprint

Emergence of Hierarchical Emotion Organization in Large Language Models

大型语言模型中层级情感组织的涌现

Maya Okawa, Bo Zhao, Eric J. Bigelow, Rose Yu, Tomer Ullman, Ekdeep Singh Lubana, Hidenori Tanaka

机构 * University of California, Berkeley（加州大学伯克利分校） ； Stanford University（斯坦福大学） ； University of Washington（华盛顿大学） ； University of Tokyo（东京大学） 纠错

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

AI总结 受情感轮理论启发，分析大型语言模型输出中情感状态间的概率依赖关系，发现模型自然形成与人类心理模型一致的层级情感树，且更大模型发展出更复杂的层级结构，同时揭示社会经济角色在情感识别中的系统性偏差。

Comments ICML 2026

Pun Intended: Multi-Agent Translation of Wordplay with Contrastive Learning and Phonetic-Semantic Embeddings for CLEF JOKER 2025 Task 2

并非双关：结合对比学习与音义嵌入的多智能体双关语翻译方法，用于CLEF JOKER 2025任务2

Russell Taylor, Benjamin Herbert, Michael Sana

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Peoples' Friendship University of Russia (RUDN University)（俄罗斯人民友谊大学） ； Joint Institute for Nuclear Research（联合核子研究中心） ； Vrije Universiteit Amsterdam（阿姆斯特丹自由大学） ； University of Skövde（斯德哥尔摩大学） 纠错

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

AI总结 本研究针对跨语言双关语翻译难题，提出结合对比学习、音义嵌入与多智能体生成器-判别器框架的三阶段方法，在CLEF JOKER 2025任务2竞赛中获第一、第二名，推动了双关语翻译研究。

Journal ref CEUR Workshop Proceedings, Vol-4038, pp. 2870-2888, 2025

Remember-R1: Mitigating Long-Context Visual Forgetting through Reinforcement Learning

Remember-R1：通过强化学习缓解长上下文视觉遗忘

Jianmin Chen, Jiaqi Tang, Wei Wei, Xiaogang Xu, Jiafei Wu, Zhe Liu, Qianzhou Wang, Yingying Yan, Botong Geng, Yuyang Xia, Lei Zhang, Qifeng Chen

机构 * Northwestern Polytechnical University（西北工业大学） ； Hong Kong University of Science and Technology（香港科技大学） ； Zhejiang University（浙江大学） 纠错

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

AI总结 该研究针对多模态大语言模型的长上下文视觉遗忘问题，提出强化学习框架Remember-R1，通过过程级监督优化视觉依赖与注意力，提升了多模态推理性能。

Comments Accepted by ACM Multimedia 2026

Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage

Lil: 在长解码阶段应用后训练稀疏注意力算法时，少即是少

Junhao Hu, Fangze Li, Mingtao Xu, Feifan Meng, Shiju Zhao, Tiancheng Hu, Ting Peng, Anmin Liu, Wenrui Huang, Chenxu Liu, Ziyue Hua, Tao Xie

机构 * SCS, Peking University, Beijing, China（北京大学信息科学与技术学院，北京，中国） ； Key Lab of HCST (PKU), MOE, Beijing, China（高等教育出版社HCST重点实验室（PKU），北京，中国） ； State Key Laboratory for Novel Software Technology, Nanjing University, China（南京大学新型软件技术国家重点实验室，中国） ； Tencent, Shenzhen, China（腾讯，深圳，中国） ； Beijing Tongming Lake Information Technology Application Innovation Center, Beijing, China（北京 Tongming Lake 信息技术应用创新中心，北京，中国） 纠错

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

AI总结 本文研究了在长解码阶段应用稀疏注意力算法时，信息丢失导致序列变长的问题，提出早停算法减少token消耗并降低精度损失。

STAC: When Innocent Tools Form Dangerous Chains for LLM Agents

STAC：当无害工具形成危险链以劫持LLM代理

Jing-Jing Li, Jianfeng He, Chao Shang, Devang Kulshreshtha, Xun Xian, Yi Zhang, Hang Su, Sandesh Swamy, Yanjun Qi

机构 * AWS AI Labs（AWS人工智能实验室） ； UC Berkeley（伯克利大学） 纠错

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

AI总结 STAC通过多轮工具链攻击揭示LLM代理的安全漏洞，提出基于推理的防御策略，显著降低攻击成功率。

Comments Long version with 15 pages in main draft and a total of 39 pages including references and appendix. Data and code \url{https://github.com/amazon-science/MultiTurnAgentAttack}

Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos

视听火烈鸟：用于长而复杂视频的开放视听智能

Sreyan Ghosh, Arushi Goel, Kaousheik Jayakumar, Lasha Koroshinadze, Nishit Anand, Siddharth Gururani, Hanrong Ye, Pritam Biswas, Yuanhang Su, Ehsan Hosseini-Asl, Sang-gil Lee, Zhifeng Kong, Jaehyeon Kim, Sungwon Kim, S Sakshi, Ramani Duraiswami, Dinesh Manocha, Andrew Tao, Mohammad Shoeybi, Bryan Catanzaro, Ming-Yu Liu, Wei Ping

机构 * NVIDIA, USA（美国NVIDIA公司） ； University of Maryland, USA（美国马里兰大学） 纠错

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

AI总结 研究提出视听火烈鸟，用于长复杂视频的联合理解与推理。贡献包括构建大规模视频集、设计三阶段课程及推理框架。实验显示其在多基准测试中表现优异，超越同类开放模型，在长复杂视听理解推理任务中竞争力强，有现实应用价值和泛化能力。

Comments Project Page: https://avflamingo.pages.dev/