| 1 | world2vec: Mechanistic world models through latent dynamics learning | Tobias Schmidt, Rodrigo Gonzalez Laiz, Krisztián Szuppinger +1 | cs.LG | 2026-10-29 |
| 2 | Reinforcement learning for control of partial differential equations | Nicolò Botteghi, Matteo Tomasetto, Andrea Manzoni | cs.LG | 2026-10-29 |
| 3 | ScienceJudge: Pattern Perturbation Augmentation for Sentence-Level Scientific Claim Verification | Chuhai Cai, Xin Chen, Min Yang +1 | cs.CL | 2026-10-29 |
| #4 | Towards Full-Text Scholarly Argument Mining using Entity-Anchored Claim Extraction | Bhuvanesh Verma, Andy Lüking, Mounika Marreddy +2 | cs.CL | 2026-10-29 |
| #5 | FIDE: Fiber-Informed Differentiable Experimental Design for Reference-Relative Law Dynamics | Pietro Zanotta, Ján Drgoňa | cs.LG | 2026-10-29 |
| #6 | Human--AI Interactions as First-Class Data: A Formal Interaction Model and Runtime for Explainable AI Collaboration | Michela Taufer, Kin Ng, Ian Lumsden +6 | cs.AI | 2026-10-29 |
| #7 | PAPERBENCHX: Can AI Reproduce Science Across Disciplines? | Ruoyu Wu, Zengji Tu, Aolong Sun +14 | cs.AI | 2026-10-29 |
| #8 | TabCUQ: Context-Uncertainty Quantification for Tabular Foundation Models | Yuebei Shi, Molei Liu, Zijian Guo | stat.ML | 2026-10-29 |
| #9 | HERA: Assessing an Autonomous Agent for Quantum Device Measurement | Zachary W. Gomez, Nathan Bittner, Jordan T. McCourt +7 | cond-mat.mes-hall | 2026-10-29 |
| #10 | Tracing the Influence of Retrieved Literature on Scientific Ideation in LLMs | Zhipin Wang, Koel Dutta Chowdhury, Christoph Leiter +1 | cs.CL | 2026-10-28 |
| #11 | Learning to Reason from Reference Samples Alone: Reinforced Adversarial Learning for Modern LLM Post-Training | Albert Bou, Javier Valdes-Aleman, Jon M. Laurent +4 | cs.AI | 2026-10-28 |
| #12 | Autonomous Quantum Measurement with Agentic AI | Eunbi Rha, Abhijatmedhi Chotrattanapituk, Mouyang Cheng +6 | cond-mat.mtrl-sci | 2026-10-28 |
| #13 | Pinpointing Pivot Points: The DECIDE Framework for Data Analysis Decision Importances | Zachary T. Rewolinski, Jan Simson, Frauke Kreuter +2 | stat.ML | 2026-10-28 |
| #14 | Learning Scientific Trajectories to Predict Future Biomedical Discoveries | Chia-Hsuan Chang, Brian Ondov, Jiang Lv +7 | cs.CL | 2026-10-28 |
| #15 | MUSE: Multi-Level Memory with Selective Runtime Injection for Scientific Coding Agents | Haoran Jin, Defu Lian, Xiting Wang +1 | cs.LG | 2026-10-28 |
| #16 | Keepace.ai: A Technical Report on a Large Language Model for Sports and Health | Keepace. ai Team, Bowen Wu, Heng Wang +12 | cs.CL | 2026-10-28 |
| #17 | CARF: Context-Aware Reasoning Supervision for Scientific Evidence Screening | Nishtha Agarwal, Adam Visokay, Astha Wahi +4 | cs.CL | 2026-10-27 |
| #18 | Assessing Language Models for Scientific Applications: Inertial Confinement Fusion as a Use Case | P. B. Radha, D. D. Meyerhofer, M. Bhattarai +11 | cs.AI | 2026-10-27 |
| #19 | Application of PDE emulators for a multi-material, multi-physics simulation problem | Diane Oyen, Morgan Jones, Adithan Kathirgamaraju +19 | cs.LG | 2026-10-27 |
| #20 | SciGame: Let Agents Play the Scientific Discovery Games in the Real and Counterfactual World | Yusheng Zhao, Bowei He, Xue Liu +1 | cs.AI | 2026-10-27 |
| #21 | Evaluating and improving AI agents for sequencing protocol understanding | Chi-Lam Poon, Michael Goneos, Zezheng Song +1 | cs.AI | 2026-10-27 |
| #22 | Can LLMs Uncover Hidden Physical Laws through Free Exploration? | Zhen Yang, Wen Wang, Xander Xu +1 | cs.CL | 2026-10-27 |
| #23 | OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery | Jiarui Yao, Ruida Wang, Tong Zhang | cs.AI | 2026-10-27 |
| #24 | Prospector: learning a compact graph traversal policy for scientific reasoning | Haiqian Yang, Markus J. Buehler | cs.AI | 2026-10-27 |
| #25 | RangeRectQuant: Compressing Scientific Fields for Every Future Rectangular Sum | Jiahao Zhang, Xinling Wen, Yu Chen | cs.CV | 2026-10-27 |
| #26 | Generative Refinement Learning for Temporal Interpolation in Scientific Machine Learning | Pu Ren, Michael W. Mahoney, N. Benjamin Erichson | cs.LG | 2026-10-27 |
| #27 | LabWorld: Learning Interactive 4D Worlds for Scientific Experimentation | Suozhi Huang, Kelsey Fu, Binxu Li +12 | cs.CV | 2026-10-27 |
| #28 | Do AI Scientists Know What's New? | Miri Liu, Xiayu Zhao, Encheng Xie +1 | cs.CL | 2026-10-27 |
| #29 | AC-JEPA: Anchored Cross-Modal Joint Embedding Predictive Architecture for Visual-to-Symbolic Translation | Chaofei Hong, Ziyang Chen, Baochen Wang +2 | cs.AI | 2026-10-27 |
| #30 | Second-order Sinkhorn Geometry and $\sqrt{n}$-Inference | Tristan Luca Saidi, Florian Gunsilius, Gonzalo Mena | stat.ML | 2026-10-27 |
| #31 | Expert lithological labels do not improve learning when used to predict marine sediment properties | John M. Aiken, William Gilpin, Thorsten W. Becker | physics.geo-ph | 2026-10-26 |
| #32 | Plenty of Room in the Middle: Revealing Opportunities on a GPU Cluster via Fine-Grained Monitoring | Andrew Sheinberg, Samyak Gupta, Kai Li | cs.AI | 2026-10-26 |
| #33 | Structure, Not Sequence: Tracking and Validating Folding Mechanisms in ESMFold's Trunk with Sparse Autoencoders | Bohan Liu, Xiaohan Fan, Wenqian Ye +1 | q-bio.QM | 2026-10-26 |
| #34 | Why and How to Do Science When AI Is Better at It: A Framework Grounded in Human Understanding and Direction | Hoda Heidari, Aydin Mohseni | cs.AI | 2026-10-26 |
| #35 | Active Learning of Conditional Generative Models via the Transport Neural Tangent Kernel | Jayoung Ryu, Kyunghyun Cho, Romain Lopez | cs.LG | 2026-10-26 |
| #36 | Distilling neural networks into equations to predict planetary instability | Simon Alford, Edward Gu, Omar Costilla-Reyes +3 | cs.LG | 2026-10-26 |
| #37 | Style over Substance? Linguistic Bias in LLM-based Peer Review Copy title | Sai Suresh Macharla Vasu, Sumedh Santosh Joshi, Philipp Christmann +6 | cs.CL | 2026-10-26 |
| #38 | Improving VLMs on Scientific Chart Analysis via Autonomous Evolution | Abhinav Sudhakar Dubey, Vidushi Goel, Kiran Rana +2 | cs.CV | 2026-10-26 |
| #39 | Selective Monocular Precession Estimation under Geometric and Evaluation Ambiguity: An Auditable Synthetic Study with ORBIT-SCOUT | Carlos Eduardo Sanoja | cs.CV | 2026-10-26 |
| #40 | The Right Fact, the Wrong Decision: SciValidityBench for Scientific Agent Memory | Yuexi Pan, Yongchao Chen | cs.AI | 2026-10-26 |
| #41 | Factorized Gradients for Scalable Highly-expressive Parametric Diffeomorphisms | Amit Aflalo, Eran Treister, Chaim Baskin +1 | cs.CV | 2026-10-26 |
| #42 | Pro-Active Inference | Skyler Wu, Yash Nair, Antoine Maechler +1 | stat.ME | 2026-10-26 |
| #43 | HARP-LoRA: Hierarchy-Conditioned Rank Projection for Low-Rank Adaptation in Scientific Table Understanding | Hossein Sholehrasa, Mohammadhossein Amini, Doina Caragea +8 | cs.CL | 2026-10-25 |
| #44 | HIFI: A Highly Efficient Framework for Statistical Inference with Foundation Models | Po-Wei Chen, Shan Yu, Chunlin Li | stat.ML | 2026-10-25 |
| #45 | A Domain-Aware Pipeline for Structured Extraction and Retrieval-Augmented Question Answering over arXiv Superconductivity Literature | Ivan Iorsh, Aleksandr Kapitonov, Ivan Filianin +2 | cs.IR | 2026-10-25 |
| #46 | Higher Reasoning Effort Improves Reference Verifiability and Changes Reasoning Summaries in GPT-5.5 | Melika Mobini, Andres Algaba, Vincent Ginis | cs.CL | 2026-10-25 |
| #47 | MatOS: An Agent Operating System for Materials Research | Dingyang Lyu, Jing Gao, Zhonghao Chang +13 | cs.AI | 2026-10-25 |
| #48 | Self-Evolution Reasoner: Continuous Optimization via Policy-Intrinsic Exploration and Exploitation | Wenhang Shi, Yiren Chen, Zhe Zhao +3 | cs.LG | 2026-10-25 |
| #49 | Deep Scientific Reasoning under Physical Constraints: Structure-Aware Spectrum Prediction | Yingheng Wang, Tao Yu, Shufeng Kong +3 | cond-mat.mtrl-sci | 2026-10-25 |
| #50 | Partial Modal Tensor Regression | Jintao Han, Li Zhang, Xuejun Ma | stat.ML | 2026-10-25 |