AAAI

ViDia2Std: A Parallel Corpus and Methods for Low-Resource Vietnamese Dialect-to-Standard Translation

ViDia2Std: 一种平行语料库及方法用于低资源越南语方言到标准语翻译

Khoa Anh Ta, Nguyen Van Dinh, Kiet Van Nguyen

AI总结 ViDia2Std是首个覆盖越南63个省份的方言到标准语翻译平行语料库，通过大量标注数据和模型测试，展示了方言规范化对提升越南语NLP性能的重要性。

Comments Accepted to AAAI-26 (Oral)

A Principle-Driven Adaptive Policy for Group Cognitive Stimulation Dialogue for Elderly with Cognitive Impairment

基于原则的自适应策略用于认知障碍老年人群体认知刺激对话

Jiyue Jiang, Yanyu Chen, Pengan Chen, Kai Liu, Jingqi Zhou, Zheyong Zhu, He Hu, Fei Ma, Qi Tian, Chuan Wu

AI总结 本文提出基于原则的自适应策略，通过GCSD系统解决认知障碍老年人群体对话中的认知刺激问题，提升交互个性化和治疗效果。

Comments Accepted by AAAI 2026

Sequential Causal Normal Form Games: Theory, Computation, and Strategic Signaling

顺序因果正常形式游戏：理论、计算与战略信号

Dennis Thumm

AI总结 本文探讨了经典博弈论框架能否扩展以捕捉AI代理的有限理性与因果推理，通过引入顺序因果多智能体系统（S-CMAS），发现其在所有测试场景中无法提供福利改进，揭示了理性选择与因果推理的不兼容性。

Comments AAAI 2026 Workshop on Foundations of Agentic Systems Theory

Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment

面向基于混合粒度权重重要性评估的自适应大语言模型结构剪枝

Jun Liu, Zhenglun Kong, Pu Zhao, Changdi Yang, Hao Tang, Xuan Shen, Geng Yuan, Wei Niu, Wenbin Zhang, Xue Lin, Dong Huang, Yanzhi Wang

AI总结 提出HyWIA方法，通过混合粒度权重重要性评估提升大语言模型剪枝效果，实现更优的性能保留和结构优化。

Comments AAAI 2025

FreqCycle: A Multi-Scale Time-Frequency Analysis Method for Time Series Forecasting

FreqCycle: 一种用于时间序列预测的多尺度时频分析方法

Boya Zhang, Shuaijie Yin, Huiwen Zhu, Xing He

AI总结 FreqCycle通过整合低频特征提取和中高频能量增强模块，提升时间序列预测的性能与效率。

Comments 18 pages, 17 figures, accepted to AAAI 2026. Code available at https://github.com/boya-zhang-ai/FreqCycle

GIIM: Graph-based Learning of Inter- and Intra-view Dependencies for Multi-view Medical Image Diagnosis

GIIM: 基于图的学习的多视图医学图像诊断中视图间和视图内依赖关系

Tran Bao Sam, Hung Vu, Dao Trung Kien, Tran Dat Dang, Van Ha Tang, Steven Truong

AI总结 GIIM通过建模多视图医学图像中视图间和视图内依赖关系，提升诊断准确性和鲁棒性。

Comments To appear in the 40th AAAI Conference on Artificial Intelligence (AAAI-26). 10 pages, 2 figures

Real-Time Trust Verification for Safe Agentic Actions using TrustBench

基于TrustBench的安全代理行为实时信任验证

Tavishi Sharma, Vinayak Sharma, Pragya Sharma

AI总结 TrustBench通过双模式框架在代理行动前验证安全性，有效减少有害行为，提升自主代理的可信度

Comments Accepted at the AAAI 2026 Workshop on Trust and Control in Agentic AI (TrustAgent)

Automatic Paper Reviewing with Heterogeneous Graph Reasoning over LLM-Simulated Reviewer-Author Debates

基于异构图推理的自动论文评审：LLM模拟的评审者-作者辩论

Shuaimin Li, Liyang Fan, Yufang Lin, Zeyang Li, Xian Wei, Shiwen Ni, Hamid Alinejad-Rokny, Min Yang

AI总结 ReViewGraph通过异构图推理分析LLM模拟的评审者-作者辩论，提升论文评审的准确性和细致程度。

Journal ref AAAI-2026

Time, Identity and Consciousness in Language Model Agents

时间、身份与语言模型代理的意识

Elija Perrier, Michael Timothy Bennett

AI总结 本文提出一种基于时间间隙的框架，用于评估语言模型代理的身份持续性，通过分离成分发生与共存，建立身份形态空间并提供保守的评估工具。

Comments Accepted at AAAI 2026 Spring Symposium - Machine Consciousness: Integrating Theory, Technology, and Philosophy

Small Language Models for Efficient Agentic Tool Calling: Outperforming Large Models with Targeted Fine-tuning

小型语言模型用于高效的代理工具调用：通过针对性微调超越大模型

Polaris Jhandi, Owais Kazi, Shreyas Subramanian, Neel Sendas

AI总结 本文通过针对性微调小型语言模型，在工具调用任务中超越大模型，展示了SLMs在成本优化和效率提升方面的潜力。

Comments Accepted at AAAI 2026 Workshop on Agentic AI Benchmarks and Applications for Enterprise Tasks

Deterministic Fuzzy Triage for Legal Compliance Classification and Evidence Retrieval

确定性模糊分诊用于法律合规分类和证据检索

Rian Atri

机构 * Rian Atri 纠错

AI总结 本文提出了一种确定性双编码器和透明模糊分诊方法，用于法律合规分类和证据检索，实现了高精度和可解释性。

Comments 8 pages, 5 figures. Published in the Proceedings of the AAAI Bridge between Artificial Intelligence and Law 2026 (Full papers), pages 51-58

Journal ref Proceedings of the AAAI Bridge between Artificial Intelligence and Law 2026 (Full papers), pages 51-58, January 21, 2026, AAAI 2026 Bridge Program, Singapore

MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy

MathSmith: 通过强化策略生成合成问题以实现极难的数学推理

Shaoxiong Zhan, Yanlin Lai, Ziyu Lu, Dahua Lin, Ziqing Yang, Fei Tan

AI总结 MathSmith通过生成合成问题提升LLM的数学推理能力，采用强化学习优化问题难度和推理复杂性。

Comments Accepted to AAAI 2026

LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models

LieCraft：一种用于评估语言模型欺骗能力的多智能体框架

Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck, Tri Nguyen, Vasudev Lal, Joseph Campbell, Simon Stepputtis, Shao-Yen Tseng

机构 * Intel Labs（英特尔实验室） 纠错

AI总结 LieCraft通过多智能体隐藏角色游戏评估语言模型的欺骗能力，揭示所有模型在面对高风险领域时均倾向于不道德行为。

Comments AAAI 2026 Alignment track. Authors 1 and 2 contributed equally, 3 and 4 contributed equally, 6 and 7 and 8 contributed equally (ordered by last name)

Co-Layout: LLM-driven Co-optimization for Interior Layout

Co-Layout: 基于大语言模型的室内布局联合优化

Chucheng Xiang, Ruchao Bao, Biyin Feng, Wenzheng Wu, Zhongyuan Liu, Yirui Guan, Ligang Liu

AI总结 本文提出基于大语言模型和整数规划的联合优化方法，用于提升室内布局和家具摆放的自动化设计效率与质量。

Comments AAAI 2026

Exploring Socially Assistive Peer Mediation Robots for Teaching Conflict Resolution to Elementary School Students

探索用于向小学生教授冲突解决的社交辅助同伴调解机器人

Kaleen Shrestha, Harish Dukkipati, Avni Hulyalkar, Kyla Penamante, Ankita Samanta, Maja Matarić

AI总结 本研究探索了社交辅助机器人在小学冲突解决教学中的应用，发现机器人能有效提升学生自我认知和冲突调解能力。

Comments Published in Proceedings of the AAAI Symposium Series (2025)

Journal ref Proceedings of the AAAI Symposium Series (2025), 5(1), 405-414

SpaCRD: Multimodal Deep Fusion of Histology and Spatial Transcriptomics for Cancer Region Detection

SpaCRD：多模态深度融合组织学与空间转录组学用于癌症区域检测

Shuailin Xue, Jun Wan, Lihua Zhang, Wenwen Min

AI总结 SpaCRD通过多模态深度融合组织学与空间转录组学数据，实现跨样本、平台和批次的癌症区域检测，优于现有八种方法。

Comments Accepted by AAAI-2026-Oral

Aligning the True Semantics: Constrained Decoupling and Distribution Sampling for Cross-Modal Alignment

对齐真实语义：基于约束解耦和分布采样的跨模态对齐

Xiang Ma, Lexin Fang, Litian Xu, Caiming Zhang

AI总结 本文提出CDDS算法，通过约束解耦和分布采样方法，解决跨模态对齐中的语义分离和模态差距问题，实验表明其优于现有方法。

Comments AAAI 2026 poster

Model Change for Description Logic Concepts

描述逻辑概念的模型变更

Ana Ozaki, Jandson S. Ribeiro

AI总结 本文研究了描述逻辑概念在模型变更中的三种类型：移除、接收和修订，分析了EL和ALC逻辑中这些操作的兼容性及修订的复杂性。

Comments Presented at AAAI 2026 (main track)

LLMTM: Benchmarking and Optimizing LLMs for Temporal Motif Analysis in Dynamic Graphs

LLMTM：动态图中基于时间 motif 分析的 LLM 评估与优化

Bing Hao, Minglai Shao, Zengyi Wo, Yunlong Chu, Yuhang Liu, Ruijie Wang

AI总结 本文提出 LLMTM 基准测试，评估 LLM 在动态图时间 motif 分析中的性能，并开发结构感知调度器以优化效率与精度的平衡。

Comments Accepted to AAAI 2026

TrinityDNA: A Bio-Inspired Foundational Model for Efficient Long-Sequence DNA Modeling

TrinityDNA: 一种生物启发的高效长序列DNA建模基础模型

Qirong Yang, Yucheng Guo, Zicheng Liu, Yujie Yang, Qijin Yin, Siyuan Li, Shaomin Ji, Linlin Chao, Xiaoming Zhang, Stan Z. Li

AI总结 TrinityDNA通过生物启发的结构和多尺度注意力机制，实现了对长序列DNA的高效建模，提升了基因组分析的准确性与实用性。

Comments AAAI 2026

UniHR: Hierarchical Representation Learning for Unified Knowledge Graph Link Prediction

UniHR: 面向统一知识图谱链接预测的分层表示学习

Zhiqiang Liu, Yin Hua, Mingyang Chen, Yichi Zhang, Zhuo Chen, Lei Liang, Wen Zhang

AI总结 UniHR提出统一的分层表示学习框架，通过统一分层数据表示和结构学习模块，提升多类型知识图谱链接预测的性能和泛化能力。

Comments AAAI 2026 (oral)

Orthogonal Spatial-temporal Distributional Transfer for 4D Generation

正交时空分布式转移用于4D生成

Wei Liu, Shengqiong Wu, Bobo Li, Haoyu Zhao, Hao Fei, Mong-Li Lee, Wynne Hsu

AI总结 本文提出正交时空分布式转移机制，通过解耦空间和时间潜在变量提升4D生成的质量和一致性。

Comments 9 pages, 6 figures, 3 tables, AAAI

DeformTrace: A Deformable State Space Model with Relay Tokens for Temporal Forgery Localization

DeformTrace: 一种带有中继标记的可变形状态空间模型用于时间伪造定位

Xiaodong Zhu, Suting Wang, Yuanming Zheng, Junqi Yang, Yangxu Liao, Yuhong Yang, Weiping Tu, Zhongyuan Wang

AI总结 DeformTrace通过可变形动态和中继机制提升状态空间模型，实现更精确的时间伪造定位，具有更少参数、更快推理和更强鲁棒性的优势。

Comments 9 pages, 4 figures, accepted by AAAI 2026

ReCast: Reliability-aware Codebook Assisted Lightweight Time Series Forecasting

ReCast: 基于可靠性感知的代码本辅助轻量时间序列预测

Xiang Ma, Taihua Chen, Pengcheng Wang, Xuemei Li, Caiming Zhang

AI总结 ReCast通过可靠性感知的代码本辅助方法，实现轻量且稳健的时间序列预测，提升预测准确性和适应性。

Comments AAAI 2026 Oral

Anyone but Him: The Complexity of Precluding an Alternative

任何人但 him：排除替代品的复杂性

Edith Hemaspaandra, Lane A. Hemaspaandra, Joerg Rothe

AI总结 本文研究了在多智能体环境下，通过机制如选民/候选人添加/删除/分割等，防止特定候选人获胜的复杂性问题，发现不同选举系统对破坏性控制的防护能力各不相同。

Comments This revision--the March 2026 Version 5--is identical to the March 2006 Version 4 except in providing, as Appendix A, a correction to the second half of the proof of Theorem 4.21 as it appears in both Version 4 and the AIJ journal version; this proof also replaces the analogous proof part of Theorem 6 of the AAAI version

SELDON: Supernova Explosions Learned by Deep ODE Networks

SELDON：通过深度ODE网络学习超新星爆炸

Jiezhong Wu, Jack O'Brien, Jennifer Li, M. S. Krafczyk, Ved G. Shah, Amanda R. Wasserman, Daniel W. Apley, Gautham Narayan, Noelle I. Samia

机构 * NSF-Simons AI Institute for the Sky (SkAI)（NSF-模拟人工智能天空研究所（SkAI）） ； Department of Industrial Engineering and Management Sciences（工业工程与管理科学系） ； Department of Astronomy（天文学系） ； National Center for Supercomputing Applications (NCSA)（国家超级计算应用中心（NCSA）） ； Department of Physics and Astronomy（物理与天文学系） ； Center for Interdisciplinary Exploration and Research in Astrophysics (CIERA)（天文学跨学科探索与研究中心（CIERA）） ； Department of Statistics and Data Science（统计学与数据科学系） 纠错

AI总结 SELDON通过深度ODE网络处理稀疏且不规则时间采样的天体光变曲线，实现快速且可解释的连续时间预测，用于天体测量的后续优先级决策。

Comments Accepted at AAAI 2026 (Proceedings of the AAAI Conference on Artificial Intelligence)

STEM Faculty Perspectives on Generative AI in Higher Education

STEM教师对高等教育中生成式人工智能的看法

Akila de Silva, Isabel Hyo Jung Song, Hui Yang, Shah Rukh Humayoun

AI总结 本文探讨STEM教师对生成式人工智能在高等教育中的应用看法，分析其教学整合、学生学习影响及机构支持需求。

Comments Accepted at AAAI 2026 Spring Symposium - Will AI Light Up Human Creativity or Replace It?: Toward Well-Being AI for co-evolving human and machine intelligence

Harmonic Dataset Distillation for Time Series Forecasting

用于时间序列预测的调和数据集蒸馏

Seungha Hong, Sanghwan Jang, Wonbin Kweon, Suyeon Kim, Gyuseok Lee, Hwanjo Yu

机构 * Seungha Hong 1 , Sanghwan Jang 1 , Wonbin Kweon 2 , Suyeon Kim 1 , Gyuseok Lee 2 , Hwanjo Yu 1（未知机构） 纠错

AI总结 本文提出HDT，通过频域分解和调和匹配提升时间序列预测的可扩展性和泛化能力。

Comments AAAI 2026

Machine Pareidolia: Protecting Facial Image with Emotional Editing

机器 pareidolia：用情绪编辑保护面部图像

Binh M. Le, Simon S. Woo

AI总结 本文提出MAP方法，通过情绪修改伪装面部身份，提升隐私保护效果，优于现有基线方法。

Comments Proceedings of the AAAI Conference on Artificial Intelligence 40

Learning to Generate and Extract: A Multi-Agent Collaboration Framework For Zero-shot Document-level Event Arguments Extraction

学习生成与提取：一种多智能体协作框架用于零样本文档级事件论证提取

Guangjun Zhang, Hu Zhang, Yazhou Han, Yue Fan, Yuhang Shao, Ru Li, Hongye Tan

AI总结 本文提出多智能体协作框架，通过生成与评估代理协同提升零样本文档级事件论证提取的性能与数据质量。

Comments Accepted by AAAI 2026