Hailing Cheng, Daqi Sun, Xinyu Lu: Learning to Rotate: Temporal and Semantic Rotary Encoding for Sequential Modeling https://arxiv.org/abs/2604.24717 https://arxiv.org/pdf/2604.24717 https://arxiv.org/html/2604.24717

Shah, Hines, Downs, Bajet, Mui, Araujo, Offutt, Rutledge, Jimenez: Case-Specific Rubrics for Clinical AI Evaluation: Methodology, Validation, and LLM-Clinician Agreement Across 823 Encounters https://arxiv.org/abs/2604.24710 https://arxiv.org/pdf/2604.24710 https://arxiv.org/html/2604.24710

Ziheng, Tang, Zhang, Lin, Yang, Long, Sun, Sun, Liang, Wu, Terzopoulos, Gao: Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft https://arxiv.org/abs/2604.24697 https://arxiv.org/pdf/2604.24697 https://arxiv.org/html/2604.24697

German Marin, Jatin Chaudhary: Governing What You Cannot Observe: Adaptive Runtime Governance for Autonomous AI Agents https://arxiv.org/abs/2604.24686 https://arxiv.org/pdf/2604.24686 https://arxiv.org/html/2604.24686

Zhenyu Zhao, Aparna Balagopalan, Adi Agrawal, Dilshoda Yergasheva, Waseem Alshikh, Daniel M. Bikel: The Price of Agreement: Measuring LLM Sycophancy in Agentic Financial Applications https://arxiv.org/abs/2604.24668 https://arxiv.org/pdf/2604.24668 https://arxiv.org/html/2604.24668

Zhuoling Li, Ha Linh Hong Tran Nguyen, Valeria Bladinieres, Maxim Romanovsky: XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation https://arxiv.org/abs/2604.24623 https://arxiv.org/pdf/2604.24623 https://arxiv.org/html/2604.24623

Robert Kirk, Alexandra Souly, Kai Fronsdal, Abby D'Cruz, Xander Davies: Evaluating whether AI models would sabotage AI safety research https://arxiv.org/abs/2604.24618 https://arxiv.org/pdf/2604.24618 https://arxiv.org/html/2604.24618

Daniel Romero Schellhorn, Till Mossakowski: NeSyCat: A Monad-Based Categorical Semantics of the Neurosymbolic ULLER Framework https://arxiv.org/abs/2604.24612 https://arxiv.org/pdf/2604.24612 https://arxiv.org/html/2604.24612

Wenke Ren, Hengxiao Guo, Wenwen Zuo, Xiaoman Zhang: A systematic evaluation of vision-language models for observational astronomical reasoning tasks https://arxiv.org/abs/2604.24589 https://arxiv.org/pdf/2604.24589 https://arxiv.org/html/2604.24589

Moeller-Grell, Shenzhang, Jiang, Dobson, Chandrabalan: FastOMOP: A Foundational Architecture for Reliable Agentic Real-World Evidence Generation on OMOP CDM data https://arxiv.org/abs/2604.24572 https://arxiv.org/pdf/2604.24572 https://arxiv.org/html/2604.24572

Bowen Jian, Rongjie Yu, Hong Wang, Liqiang Wang, Zihang Zou: Towards Lawful Autonomous Driving: Deriving Scenario-Aware Driving Requirements from Traffic Laws and Regulations https://arxiv.org/abs/2604.24562 https://arxiv.org/pdf/2604.24562 https://arxiv.org/html/2604.24562

Michael Tryfan Matthews, Anssi Kanervisto, Jakob Foerster, Pierluca D'Oro, Scott Fujimoto, Mikael Henaff: Hierarchical Behaviour Spaces https://arxiv.org/abs/2604.24558 https://arxiv.org/pdf/2604.24558 https://arxiv.org/html/2604.24558

Alessio Sordo, Lingxiao Du, Meeka-Hanna Lenisa, Evgeny Bogdanov, Maxim Romanovsky: STELLAR-E: a Synthetic, Tailored, End-to-end LLM Application Rigorous Evaluator https://arxiv.org/abs/2604.24544 https://arxiv.org/pdf/2604.24544 https://arxiv.org/html/2604.24544

Diego Candia-Rivera (NERV): Interoceptive machine framework: Toward interoception-inspired regulatory architectures in artificial intelligence https://arxiv.org/abs/2604.24527 https://arxiv.org/pdf/2604.24527 https://arxiv.org/html/2604.24527

Dahlia Shehata, Ming Li: Beyond the Attention Stability Boundary: Agentic Self-Synthesizing Reasoning Protocols https://arxiv.org/abs/2604.24512 https://arxiv.org/pdf/2604.24512 https://arxiv.org/html/2604.24512

Siavash Golkar, et al.: MIMIC: A Generative Multimodal Foundation Model for Biomolecules https://arxiv.org/abs/2604.24506 https://arxiv.org/pdf/2604.24506 https://arxiv.org/html/2604.24506

Johannes Moll, et al.: Agentic clinical reasoning over longitudinal myeloma records: a retrospective evaluation against expert consensus https://arxiv.org/abs/2604.24473 https://arxiv.org/pdf/2604.24473 https://arxiv.org/html/2604.24473

Sinin Zhang, Yunfei Xie, Yuxuan Cheng, Haoyu Zhang, Tong Zhang: PhysNote: Self-Knowledge Notes for Evolvable Physical Reasoning in Vision-Language Model https://arxiv.org/abs/2604.24443 https://arxiv.org/pdf/2604.24443 https://arxiv.org/html/2604.24443

Byeonggeuk Lim, JungMin Yun, Junehyoung Kwon, Kyeonghyun Kim, YoungBin Kim: Aligning with Your Own Voice: Self-Corrected Preference Learning for Hallucination Mitigation in LVLMs https://arxiv.org/abs/2604.24395 https://arxiv.org/pdf/2604.24395 https://arxiv.org/html/2604.24395

No\'emie Cohen (Airbus CR\&T), M\'elanie Ducoffe (Airbus CR\&T), Christophe Gabreau, Claire Pagetti, Xavier Pucel: Certified geometric robustness -- Super-DeepG https://arxiv.org/abs/2604.24379 https://arxiv.org/pdf/2604.24379 https://arxiv.org/html/2604.24379

Patrick Kr\"uger, Hanno Gottschalk, Werner Krebs, Bastian Werdelmann: Generative Design of a Gas Turbine Combustor Using Invertible Neural Networks https://arxiv.org/abs/2604.24322 https://arxiv.org/pdf/2604.24322 https://arxiv.org/html/2604.24322

Hee-Kyong Yoo, Wonbae Kim, Hyocheol Ahn: Adaptive ToR: Complexity-Aware Tree-Based Retrieval for Pareto-Optimal Multi-Intent NLU https://arxiv.org/abs/2604.24219 https://arxiv.org/pdf/2604.24219 https://arxiv.org/html/2604.24219

Thomas Bailleux, Tanmoy Mukherjee, Emmanuel Lonca, Pierre Marquis, Zied Bouraoui: Explanation Quality Assessment as Ranking with Listwise Rewards https://arxiv.org/abs/2604.24176 https://arxiv.org/pdf/2604.24176 https://arxiv.org/html/2604.24176

Tanmoy Mukherjee, Thomas Bailleux, Pierre Marquis, Zied Bouraoui: Credal Concept Bottleneck Models for Epistemic-Aleatoric Uncertainty Decomposition https://arxiv.org/abs/2604.24170 https://arxiv.org/pdf/2604.24170 https://arxiv.org/html/2604.24170

Ashmi Banerjee, Adithi Satish, Wolfgang W\"orndl, Yashar Deldjoo: Multi-Dimensional Evaluation of Sustainable City Trips with LLM-as-a-Judge and Human-in-the-Loop https://arxiv.org/abs/2604.24158 https://arxiv.org/pdf/2604.24158 https://arxiv.org/html/2604.24158

Gadi Lavi: Right-to-Act: A Pre-Execution Non-Compensatory Decision Protocol for AI Systems https://arxiv.org/abs/2604.24153 https://arxiv.org/pdf/2604.24153 https://arxiv.org/html/2604.24153

Moritz Link, Jonathan Hoss, Noah Klarmann: An Analysis of the Coordination Gap between Joint and Modular Learning for Job Shop Scheduling with Transportation Resources https://arxiv.org/abs/2604.24117 https://arxiv.org/pdf/2604.24117 https://arxiv.org/html/2604.24117

Jan K\v{r}et\'insk\'y, Tobias Meggendorfer, Maximilian Prokop: SemML 2.0: Synthesizing Controllers for LTL https://arxiv.org/abs/2604.24102 https://arxiv.org/pdf/2604.24102 https://arxiv.org/html/2604.24102

Hikmat Karimov, Rahid Zahid Alekberli: The Kerimov-Alekberli Model: An Information-Geometric Framework for Real-Time System Stability https://arxiv.org/abs/2604.24083 https://arxiv.org/pdf/2604.24083 https://arxiv.org/html/2604.24083

Hikmat Karimov, Rahid Zahid Alekberli: An Information-Geometric Framework for Stability Analysis of Large Language Models under Entropic Stress https://arxiv.org/abs/2604.24076 https://arxiv.org/pdf/2604.24076 https://arxiv.org/html/2604.24076

Liangru Xiang, Yuxi Ma, Zhihao Cao, Yixin Zhu, Song-Chun Zhu: Grounding Before Generalizing: How AI Differs from Humans in Causal Transfer https://arxiv.org/abs/2604.24062 https://arxiv.org/pdf/2604.24062 https://arxiv.org/html/2604.24062

Bin Chen, Shouliang Zhu, Beidan Liu, Yong Zhao, Tianle Pu, Huichun Li, Zhengqiu Zhu: A2DEPT: Large Language Model-Driven Automated Algorithm Design via Evolutionary Program Trees https://arxiv.org/abs/2604.24043 https://arxiv.org/pdf/2604.24043 https://arxiv.org/html/2604.24043

Yuxuan Gao, Megan Wang, Yi Ling Yu: AgentPulse: A Continuous Multi-Signal Framework for Evaluating AI Agents in Deployment https://arxiv.org/abs/2604.24038 https://arxiv.org/pdf/2604.24038 https://arxiv.org/html/2604.24038

Chenyang An, Qihao Ye, Minghao Pan, Jiayaun Zhang: QED: An Open-Source Multi-Agent System for Generating Mathematical Proofs on Open Problems https://arxiv.org/abs/2604.24021 https://arxiv.org/pdf/2604.24021 https://arxiv.org/html/2604.24021

Ruifeng Yuan, Wanxing Chang, Weiwei Cao, Bowen Shi, Zhongyu Wei, Ling Zhang, Jianpeng Zhang: CT-FineBench: A Diagnostic Fidelity Benchmark for Fine-Grained Evaluation of CT Report Generation https://arxiv.org/abs/2604.24001 https://arxiv.org/pdf/2604.24001 https://arxiv.org/html/2604.24001

M. Meng: Failure-Centered Runtime Evaluation for Deployed Trilingual Public-Space Agents https://arxiv.org/abs/2604.23990 https://arxiv.org/pdf/2604.23990 https://arxiv.org/html/2604.23990

Jack King, Evelina Fedorenko, Eghbal A. Hosseini: Representational Curvature Modulates Behavioral Uncertainty in Large Language Models https://arxiv.org/abs/2604.23985 https://arxiv.org/pdf/2604.23985 https://arxiv.org/html/2604.23985

Aydin Ayanzadeh, Tim Oates: LLM-Guided Agentic Floor Plan Parsing for Accessible Indoor Navigation of Blind and Low-Vision People https://arxiv.org/abs/2604.23970 https://arxiv.org/pdf/2604.23970 https://arxiv.org/html/2604.23970

Ioannis Bilionis, Ricardo C. Berrios, Luis Fernandez-Luque, Carlos Castillo: An empirical evaluation of the risks of AI model updates using clinical data: stability, arbitrariness, and fairness https://arxiv.org/abs/2604.23954 https://arxiv.org/pdf/2604.23954 https://arxiv.org/html/2604.23954

Rhea Makkuni, Ananya Joshi: Context-Aware Hospitalization Forecasting Evaluations for Decision Support using LLMs https://arxiv.org/abs/2604.23949 https://arxiv.org/pdf/2604.23949 https://arxiv.org/html/2604.23949

Shiven Agarwal, Yash Shah, Ashish Raj Shekhar, Priyanuj Bordoloi, Vivek Gupta: GamED.AI: A Hierarchical Multi-Agent Framework for Automated Educational Game Generation https://arxiv.org/abs/2604.23947 https://arxiv.org/pdf/2604.23947 https://arxiv.org/html/2604.23947

N., Kubicek-Sutherland, Negrete, Gnanakaran: Agentic AI platforms for autonomous training and rule induction of human-human and virus-human protein-protein interactions https://arxiv.org/abs/2604.23924 https://arxiv.org/pdf/2604.23924 https://arxiv.org/html/2604.23924

Jiazhao Shi: LLM-Augmented Traffic Signal Control with LSTM-Based Traffic State Prediction and Safety-Constrained Decision Support https://arxiv.org/abs/2604.23902 https://arxiv.org/pdf/2604.23902 https://arxiv.org/html/2604.23902

Andrey Fradkin, Rohit Krishnan: MarketBench: Evaluating AI Agents as Market Participants https://arxiv.org/abs/2604.23897 https://arxiv.org/pdf/2604.23897 https://arxiv.org/html/2604.23897

Alexander Bering: ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems https://arxiv.org/abs/2604.23878 https://arxiv.org/pdf/2604.23878 https://arxiv.org/html/2604.23878

Thomas Bartz-Beielstein, Eva Bartz: Time-Series Forecasting in Safety-Critical Environments: An EU-AI-Act-Compliant Open-Source Package / Zeitreihenprognose in sicherheitskritischen Umgebunge... https://arxiv.org/abs/2604.23859 https://arxiv.org/pdf/2604.23859 https://arxiv.org/html/2604.23859

Andreza M. C. Falcao, Filipe R. Cordeiro: Does Machine Unlearning Preserve Clinical Safety? A Risk Analysis for Medical Image Classification https://arxiv.org/abs/2604.23854 https://arxiv.org/pdf/2604.23854 https://arxiv.org/html/2604.23854

Boqin Yuan, Renchu Song, Yue Su, Sen Yang, Jing Qin: ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation https://arxiv.org/abs/2604.23853 https://arxiv.org/pdf/2604.23853 https://arxiv.org/html/2604.23853

John Winnicki, Abeynaya Gnanasekaran, Eric Darve: Domain-Filtered Knowledge Graphs from Sparse Autoencoder Features https://arxiv.org/abs/2604.23829 https://arxiv.org/pdf/2604.23829 https://arxiv.org/html/2604.23829

Sophie Chiang, Tom Brennan, Fethiye Irmak Dogan, Jiaee Cheong, Hatice Gunes: FAIR_XAI: Improving Multimodal Foundation Model Fairness via Explainability for Wellbeing Assessment https://arxiv.org/abs/2604.23786 https://arxiv.org/pdf/2604.23786 https://arxiv.org/html/2604.23786