Zhaoyang Wang, Canwen Xu, Boyi Liu, Yite Wang, Siwei Han, Zhewei Yao, Huaxiu Yao, Yuxiong He: Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning https://arxiv.org/abs/2602.10090 https://arxiv.org/pdf/2602.10090 https://arxiv.org/html/2602.10090

Mariia Ponomarenko, Sepideh Abedini, Masoumeh Shafieinejad, D. B. Emerson, Shubhankar Mohapatra, Xi He: CAPID: Context-Aware PII Detection for Question-Answering Systems https://arxiv.org/abs/2602.10074 https://arxiv.org/pdf/2602.10074 https://arxiv.org/html/2602.10074

Dawn Lawrie, Sean MacAvaney, James Mayfield, Luca Soldaini, Eugene Yang, Andrew Yates: Overview of the TREC 2025 RAGTIME Track https://arxiv.org/abs/2602.10024 https://arxiv.org/pdf/2602.10024 https://arxiv.org/html/2602.10024

Huang, Huang, Zhao, Liu, Zhang, Shi, Li, Sun, Wu, Hu, Bai, Cao: QP-OneModel: A Unified Generative LLM for Multi-Task Query Understanding in Xiaohongshu Search https://arxiv.org/abs/2602.09901 https://arxiv.org/pdf/2602.09901 https://arxiv.org/html/2602.09901

Yuhao Zheng, Li'an Zhong, Yi Wang, Rui Dai, Kaikui Liu, Xiangxiang Chu, Linyuan Lv, Philip Torr, Kevin Qinghong Lin: Code2World: A GUI World Model via Renderable Code Generation https://arxiv.org/abs/2602.09856 https://arxiv.org/pdf/2602.09856 https://arxiv.org/html/2602.09856

Wang, Li, Zhang, Zhao, Zou, Li, Cui, Zhang, Wei, Xu, Huang, Xu, Hu, He, Xie, Kang, Chen, Yu, Yu, Chen, Di, Feng, Hu, Liu, Wang, Yang: Covo-Audio Technical Report https://arxiv.org/abs/2602.09823 https://arxiv.org/pdf/2602.09823 https://arxiv.org/html/2602.09823

Manon Reusens, Sofie Goethals, Toon Calders, David Martens: Would a Large Language Model Pay Extra for a View? Inferring Willingness to Pay from Subjective Choices https://arxiv.org/abs/2602.09802 https://arxiv.org/pdf/2602.09802 https://arxiv.org/html/2602.09802

Andres Saurez, Neha Sengar, Dongsoo Har: Circuit Fingerprints: How Answer Tokens Encode Their Geometrical Path https://arxiv.org/abs/2602.09784 https://arxiv.org/pdf/2602.09784 https://arxiv.org/html/2602.09784

Andres Saurez, Yousung Lee, Dongsoo Har: Why Linear Interpretability Works: Invariant Subspaces as a Result of Architectural Constraints https://arxiv.org/abs/2602.09783 https://arxiv.org/pdf/2602.09783 https://arxiv.org/html/2602.09783

Kun Chen, Peng Shi, Fanfan Liu, Haibo Qiu, Zhixiong Zeng, Siqi Yang, Wenji Mao: Flexible Entropy Control in RLVR with Gradient-Preserving Perspective https://arxiv.org/abs/2602.09782 https://arxiv.org/pdf/2602.09782 https://arxiv.org/html/2602.09782

Zhao, Yang, Li, He, Li, Jin, Veeravalli, Gupta, Arora: AlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical Algorithms https://arxiv.org/abs/2602.09464 https://arxiv.org/pdf/2602.09464 https://arxiv.org/html/2602.09464

Zhang, Zhang, Fei, Bao, Chen, Lei, Liu, Sun, Xiao, Ye, Zhang, Zhu, Wen, Shum: SWE-AGI: Benchmarking Specification-Driven Software Construction with MoonBit in the Era of Autonomous Agents https://arxiv.org/abs/2602.09447 https://arxiv.org/pdf/2602.09447 https://arxiv.org/html/2602.09447

Waris Quamer, Mu-Ruei Tseng, Ghady Nasrallah, Ricardo Gutierrez-Osuna: TVTSyn: Content-Synchronous Time-Varying Timbre for Streaming Voice Conversion and Anonymization https://arxiv.org/abs/2602.09389 https://arxiv.org/pdf/2602.09389 https://arxiv.org/html/2602.09389

Xu, Zhou, Ma, Ding, Yan, Xiao, Li, Geng, Han, Chen, Deng: LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and Diagnosis https://arxiv.org/abs/2602.09379 https://arxiv.org/pdf/2602.09379 https://arxiv.org/html/2602.09379

Michail S. Alexiou, J. Sukarno Mertoguno: Not-in-Perspective: Towards Shielding Google's Perspective API Against Adversarial Negation Attacks https://arxiv.org/abs/2602.09343 https://arxiv.org/pdf/2602.09343 https://arxiv.org/html/2602.09343

Christine de Kock, Eduard Hovy: Triggered: A Statistical Analysis of Environmental Influences on Extremist Groups https://arxiv.org/abs/2602.09289 https://arxiv.org/pdf/2602.09289 https://arxiv.org/html/2602.09289

Giordano De Marzo, David Garcia: Collective Behavior of AI Agents: the Case of Moltbook https://arxiv.org/abs/2602.09270 https://arxiv.org/pdf/2602.09270 https://arxiv.org/html/2602.09270

Xingjian Zhang, Sophia Moylan, Ziyang Xiong, Qiaozhu Mei, Yichen Luo, Jiaqi W. Ma: FlyAOC: Evaluating Agentic Ontology Curation of Drosophila Scientific Knowledge Bases https://arxiv.org/abs/2602.09163 https://arxiv.org/pdf/2602.09163 https://arxiv.org/html/2602.09163

Haitao Jiang, Lin Ge, Hengrui Cai, Rui Song: PABU: Progress-Aware Belief Update for Efficient LLM Agents https://arxiv.org/abs/2602.09138 https://arxiv.org/pdf/2602.09138 https://arxiv.org/html/2602.09138

Rohit Dutta, Paramita Koley, Soham Poddar, Janardan Misra, Sanjay Podder, Naveen Balani, Saptarshi Ghosh, Niloy Ganguly: Benchmarking the Energy Savings with Speculative Decoding Strategies https://arxiv.org/abs/2602.09113 https://arxiv.org/pdf/2602.09113 https://arxiv.org/html/2602.09113

, , Gao, Gu, Liu, Qiu, Shen, Wen, Xia, Xu, Zeng, Zhou, Zhou, Chen, Dai, Dou, Gong, Guo, Guo, Li, Li, Lin, Zhou, Zhu, Chen, Guo, Meng, Wang: UI-Venus-1.5 Technical Report https://arxiv.org/abs/2602.09082 https://arxiv.org/pdf/2602.09082 https://arxiv.org/html/2602.09082

Mohamed Afane, Kayla Laufer, Wenqi Wei, Ying Mao, Junaid Farooq, Ying Wang, Juntao Chen: Quantum-Audit: Evaluating the Reasoning Limits of LLMs on Quantum Computing https://arxiv.org/abs/2602.10092 https://arxiv.org/pdf/2602.10092 https://arxiv.org/html/2602.10092

Xuehang Guo, Zhiyong Lu, Tom Hope, Qingyun Wang: Anagent For Enhancing Scientific Table & Figure Analysis https://arxiv.org/abs/2602.10081 https://arxiv.org/pdf/2602.10081 https://arxiv.org/html/2602.10081

Delvin Ce Zhang, Suhan Cui, Zhelin Chu, Xianren Zhang, Dongwon Lee: MEVER: Multi-Modal and Explainable Claim Verification with Graph-based Evidence Retrieval https://arxiv.org/abs/2602.10023 https://arxiv.org/pdf/2602.10023 https://arxiv.org/html/2602.10023

Wenxuan Xie, Yujia Wang, Xin Tan, Chaochao Lu, Xia Hu, Xuhong Wang: Decoupled Reasoning with Implicit Fact Tokens (DRIFT): A Dual-Model Framework for Efficient Long-Context Inference https://arxiv.org/abs/2602.10021 https://arxiv.org/pdf/2602.10021 https://arxiv.org/html/2602.10021

Homaira Huda Shomee, Rochana Chaturvedi, Yangxinyu Xie, Tanwi Mallick: SCORE: Specificity, Context Utilization, Robustness, and Relevance for Reference-Free LLM Evaluation https://arxiv.org/abs/2602.10017 https://arxiv.org/pdf/2602.10017 https://arxiv.org/html/2602.10017

Khoa Anh Nguyen, Long Minh Hoang, Nghia Hieu Nguyen, Luan Thanh Nguyen, Ngan Luu-Thuy Nguyen: ViSpeechFormer: A Phonemic Approach for Vietnamese Automatic Speech Recognition https://arxiv.org/abs/2602.10003 https://arxiv.org/pdf/2602.10003 https://arxiv.org/html/2602.10003

Xiulin Yang, Arianna Bisazza, Nathan Schneider, Ethan Gotlieb Wilcox: A Unified Assessment of the Poverty of the Stimulus Argument for Neural Language Models https://arxiv.org/abs/2602.09992 https://arxiv.org/pdf/2602.09992 https://arxiv.org/html/2602.09992

Cao, Thai, Nguyen, Nguyen, Nguyen: ViMultiChoice: Toward a Method That Gives Explanation for Multiple-Choice Reading Comprehension in Vietnamese https://arxiv.org/abs/2602.09961 https://arxiv.org/pdf/2602.09961 https://arxiv.org/html/2602.09961

Shuaiyi Nie, Siyu Ding, Wenyuan Zhang, Linhao Yu, Tianmeng Yang, Yao Chen, Tingwen Liu, Weichong Yin, Yu Sun, Hua Wu: ATTNPO: Attention-Guided Process Supervision for Efficient Reasoning https://arxiv.org/abs/2602.09953 https://arxiv.org/pdf/2602.09953 https://arxiv.org/html/2602.09953

William Lugoloobi, Thomas Foster, William Bankes, Chris Russell: LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations https://arxiv.org/abs/2602.09924 https://arxiv.org/pdf/2602.09924 https://arxiv.org/html/2602.09924

Tilahun Yeshambel, Moncef Garouani, Josiane Mothe: AmharicIR+Instr: A Two-Dataset Resource for Neural Retrieval and Instruction Tuning https://arxiv.org/abs/2602.09914 https://arxiv.org/pdf/2602.09914 https://arxiv.org/html/2602.09914

Wang, Li, Liu, Chen, Hou, Qi, Li, Zhang, Ye, Liu, Chen, Zhang, Yu: The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies https://arxiv.org/abs/2602.09877 https://arxiv.org/pdf/2602.09877 https://arxiv.org/html/2602.09877

Chung-En Sun, Ge Yan, Zimo Wang, Tsui-Wei Weng: Steer2Edit: From Activation Steering to Component-Level Editing https://arxiv.org/abs/2602.09870 https://arxiv.org/pdf/2602.09870 https://arxiv.org/html/2602.09870

Johan Sofalas, Dilushri Pavithra, Nevidu Jayatilleke, Ruvan Weerasinghe: SinFoS: A Parallel Dataset for Translating Sinhala Figures of Speech https://arxiv.org/abs/2602.09866 https://arxiv.org/pdf/2602.09866 https://arxiv.org/html/2602.09866

Yayun Zhang, Guanyi Chen, Fahime Same, Saad Mahamood, Tingting He: How Do People Quantify Naturally: Evidence from Mandarin Picture Description https://arxiv.org/abs/2602.09838 https://arxiv.org/pdf/2602.09838 https://arxiv.org/html/2602.09838

Bakhtawar Ahtisham, Kirk Vanacore, Zhuqian Zhou, Jinsook Lee, Rene F. Kizilcec: LLM Reasoning Predicts When Models Are Right: Evidence from Coding Classroom Discourse https://arxiv.org/abs/2602.09832 https://arxiv.org/pdf/2602.09832 https://arxiv.org/html/2602.09832

Abdulmuizz Khalak, Abderrahmane Issam, Gerasimos Spanakis: From FusHa to Folk: Exploring Cross-Lingual Transfer in Arabic Language Models https://arxiv.org/abs/2602.09826 https://arxiv.org/pdf/2602.09826 https://arxiv.org/html/2602.09826

Zhang, Zhang, Chen, Liu, Li, Sun, Yuan, Puspitasari, Han, Wang, Bae, Yang: Text summarization via global structure awareness https://arxiv.org/abs/2602.09821 https://arxiv.org/pdf/2602.09821 https://arxiv.org/html/2602.09821

Khang Ly, Georgios Cheirmpos, Adrian Raudaschl, Christopher James, Seyed Amin Tabatabaei: AnalyticsGPT: An LLM Workflow for Scientometric Question Answering https://arxiv.org/abs/2602.09817 https://arxiv.org/pdf/2602.09817 https://arxiv.org/html/2602.09817

Daniel Kaiser, Arnoldo Frigessi, Ali Ramezani-Kebrya, Benjamin Ricaud: Decomposing Reasoning Efficiency in Large Language Models https://arxiv.org/abs/2602.09805 https://arxiv.org/pdf/2602.09805 https://arxiv.org/html/2602.09805

Seydou Diallo, Yacouba Diarra, Mamadou K. Keita, Panga Azazia Kamat\'e, Adam Bouno Kampo, Aboubacar Ouattara: Where Are We At with Automatic Speech Recognition for the Bambara Language? https://arxiv.org/abs/2602.09785 https://arxiv.org/pdf/2602.09785 https://arxiv.org/html/2602.09785

Kohei Oda, Hiroya Takamura, Kiyoaki Shirai, Natthawut Kertkeidkachorn: Improving Interpretability of Lexical Semantic Change with Neurobiological Features https://arxiv.org/abs/2602.09760 https://arxiv.org/pdf/2602.09760 https://arxiv.org/html/2602.09760

Maciej Rapacz, Aleksander Smywi\'nski-Pohl: Targum -- A Multilingual New Testament Translation Corpus https://arxiv.org/abs/2602.09724 https://arxiv.org/pdf/2602.09724 https://arxiv.org/html/2602.09724

Christian Buck, et al.: AI-Assisted Scientific Assessment: A Case Study on Climate Change https://arxiv.org/abs/2602.09723 https://arxiv.org/pdf/2602.09723 https://arxiv.org/html/2602.09723

Longhuan Xu, Cunjian Chen, Feng Yin: Unsupervised Layer-Wise Dynamic Test Time Adaptation for LLMs https://arxiv.org/abs/2602.09719 https://arxiv.org/pdf/2602.09719 https://arxiv.org/html/2602.09719

Yiming Shu, Pei Liu, Tiange Zhang, Ruiyang Gao, Jun Ma, Chen Sun: TraceMem: Weaving Narrative Memory Schemata from User Conversational Traces https://arxiv.org/abs/2602.09712 https://arxiv.org/pdf/2602.09712 https://arxiv.org/html/2602.09712

Abdulhai Alali, Abderrahmane Issam: Maastricht University at AMIYA: Adapting LLMs for Dialectal Arabic using Fine-tuning and MBR Decoding https://arxiv.org/abs/2602.09703 https://arxiv.org/pdf/2602.09703 https://arxiv.org/html/2602.09703

Attieh, Mickus, Ligozat, N\'ev\'eol, Tiedemann: Life Cycle-Aware Evaluation of Knowledge Distillation for Machine Translation: Environmental Impact and Translation Quality Trade-offs https://arxiv.org/abs/2602.09691 https://arxiv.org/pdf/2602.09691 https://arxiv.org/html/2602.09691

Sieun Hyeon, Jusang Oh, Sunghwan Steve Cho, Jaeyoung Do: MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answering https://arxiv.org/abs/2602.09642 https://arxiv.org/pdf/2602.09642 https://arxiv.org/html/2602.09642