| 1 | world2vec: Mechanistic world models through latent dynamics learning | Tobias Schmidt, Rodrigo Gonzalez Laiz, Krisztián Szuppinger +1 | cs.LG | 2026-10-29 |
| 2 | FARMS: A Verifiable Foundation for Automated Computational Science | Di Wu, Ling Liang, Haizhao Yang | cs.AI | 2026-10-29 |
| 3 | Discovering Interpretable Acoustic Features in Autoregressive Voice-Cloning TTS Models | Anuj Diwan, David Harwath, Eunsol Choi | eess.AS | 2026-10-29 |
| #4 | Framework-Conditional Open Materials Generation | Maya M. Martirossyan, Hillary Pan, Philipp Höllmer +1 | cs.LG | 2026-10-29 |
| #5 | Bridging Semantics and Structure: A Theoretically Grounded Framework for Link Prediction on TAGs | Chen Shao, Ruirui Wang, Tobias Kafer +1 | cs.AI | 2026-10-29 |
| #6 | A Negotiation-Aware Hybrid LLM Framework for Intent Interpretation and Service Discovery | Wided Meflah, Hayet Brabra, Walid Gaaloul | cs.AI | 2026-10-29 |
| #7 | TACFormer: Transformer-Based Generative Model for Target-Conditioned De Novo PROTAC Design | Yossra Gharbi, Rocío Mercado | cs.LG | 2026-10-29 |
| #8 | MoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery | Yikun Zhang, Xiwei Cheng, Mingze Yuan +15 | cs.AI | 2026-10-29 |
| #9 | Semantic Mismapping in Generalized Category Discovery: Evaluation and Mitigation | Zitai Wang, Qianqian Xu, Cong Hua +4 | cs.CV | 2026-10-29 |
| #10 | LLM-Assisted Optimization for Simulation-Based Redesign | Chan-Eui Song, Jeremy J. Michalek, Christopher McComb | cs.AI | 2026-10-29 |
| #11 | Reasoning or Pattern Exploitation? Mechanistic Insights from RL-Trained Language Models | Aishik Nagar, Cheston Tan | cs.AI | 2026-10-29 |
| #12 | PALATE: Pretrained Autoregressive LATent Embeddings | Sizhang Zhao, Praveen Gondhi, Bin Li +1 | cs.IR | 2026-10-29 |
| #13 | Representation Complexity Along Learning Trajectories: Trading Width for Precision and Time | Ryan Singh, Miguel De Llanza, Christopher L. Buckley | cs.LG | 2026-10-28 |
| #14 | Assessing feature scorer results on high-dimensional datasets with t-SNE | Bruno Iochins Grisci, Mario Inostroza-Ponta, Márcio Dorn | cs.LG | 2026-10-28 |
| #15 | Discovery of Diverse and Realistic Financial Tail-Risk Using Generative Flow Networks | Adir Serruya, Gilad Katz | cs.LG | 2026-10-28 |
| #16 | Discovering Jailbreaks via Curriculum of Models | Michał Burzyński, Noah T. Rossi, Shomit Basu +1 | cs.LG | 2026-10-28 |
| #17 | Manifest-Assisted Retrieval in Artificial Intelligence Search: Evidence Gaps and a Security Evaluation | Gangzhen Qian, Kainan Zhou, Chuhong Xu +5 | cs.CR | 2026-10-28 |
| #18 | Verification-Guided Retrosynthesis: Reaction Feedback and Evidence Timing | Hongxuan Shi, Hankz Hankui Zhuo | cs.AI | 2026-10-28 |
| #19 | Interpretable Feature Discovery from Unstructured Data Using LLMs and Statistical Choice Models | Baptiste Arnaudo, Amine Bennouna, Sébastien Martin | stat.ML | 2026-10-27 |
| #20 | EARS-Info: Information-Aware Event-Driven Reallocation for Multi-Robot Exploration | Kabeh Mohsenzadegan, Vahid Tavakkoli, Kyandoghere Kyamakya | cs.RO | 2026-10-27 |
| #21 | Application of PDE emulators for a multi-material, multi-physics simulation problem | Diane Oyen, Morgan Jones, Adithan Kathirgamaraju +19 | cs.LG | 2026-10-27 |
| #22 | 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 |
| #23 | Can LLMs Uncover Hidden Physical Laws through Free Exploration? | Zhen Yang, Wen Wang, Xander Xu +1 | cs.CL | 2026-10-27 |
| #24 | OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery | Jiarui Yao, Ruida Wang, Tong Zhang | cs.AI | 2026-10-27 |
| #25 | Grounding LLM Agents in Business Processes: Process-Aware Knowledge Graphs for Reliable Multi-Step Service Invocation | Saiful Khan, Afrah Farea | cs.AI | 2026-10-27 |
| #26 | Threshold Compatibility and Support-Selection Diagnostics in Neural Discovery of Partial Differential Equations | Zeen Song | cs.LG | 2026-10-27 |
| #27 | AI-Assisted Discovery of CNOT Decompositions for Quantum Permutations on Constrained Topologies | Daniele Lizzio Bosco, Jacopo Cossio, Simone Faro +4 | cs.AI | 2026-10-27 |
| #28 | Dependency Graphs of Mathematical Arguments: Representation, Structural Measurement, and Proof Review | Eunji Park | cs.AI | 2026-10-27 |
| #29 | HeteGCD: Statistics-Aware Dual-Prototype Learning for Generalized Category Discovery on Heterophilous Graphs | Xuanzhi Xi, Tongze Zhang, Zhili Qin +5 | cs.LG | 2026-10-27 |
| #30 | Dream-COP: Guiding Algorithm Discovery for Combinatorial Optimization Problems in an Experience World | Kuan Xu, Jianming Wang, Ni Zhang +3 | cs.LG | 2026-10-27 |
| #31 | Do AI Scientists Know What's New? | Miri Liu, Xiayu Zhao, Encheng Xie +1 | cs.CL | 2026-10-27 |
| #32 | Spatial-Frequency Learning for Scanning Transmission Electron Microscopy Image Enhancement | Hesong Li, Ying Fu, Ziqi Wu +2 | cs.CV | 2026-10-27 |
| #33 | HELICS: Biobank-scale Conditional Synthetic Genome Generation via Latent Flow Matching | Ahmad Abdel-Azim, Xihong Lin | q-bio.GN | 2026-10-26 |
| #34 | EVA-Flow: Learning Shared Chemistry for Unified Environment-Aware Molecular Conformation Generation | Bing Yan, Anuroop Sriram, Zachary Ward Ulissi +3 | cs.LG | 2026-10-26 |
| #35 | Adversary Brains: Hypothesis-Based Logical Signatures for Threat Actor Detection with LLMs | Gadi Evron | cs.CR | 2026-10-26 |
| #36 | Agentic Algorithm Design: LLMs that Propose, Formalise, and Prove Runtime Bounds for Evolutionary Algorithms in Lean | Per Kristian Lehre | cs.AI | 2026-10-26 |
| #37 | Multi-Horizon Future Discovery for Physics-Informed Exploration | Shuwei Wang, Qiang Guan, Brian Qiu +5 | cs.LG | 2026-10-26 |
| #38 | Skill$^{\infty}$: Recursive Self-Improvement for Agent Skill Optimization | Wangcheng Tao, Zhanglu Yan, Han Wu +1 | cs.AI | 2026-10-26 |
| #39 | Autonomous Structural Discovery Of Bioprocess Dynamics And Kinetics Via LLM-Driven Agents | Erdal Aydin, Yaman Arkun | math.OC | 2026-10-26 |
| #40 | RSIV-Harness: A Recursive Self-Improvement Harness Framework for Open-Domain Conversational Text-to-Visualization | Jiawei Lu, Chen Zhang, Jinwei Lu +3 | cs.AI | 2026-10-26 |
| #41 | PROBE: Frontier Coding Agents Find Different Bugs Than Maintainers Fix | Marco Paina, Mark Niklas Müller, Niels Mündler-Sasahara +1 | cs.SE | 2026-10-26 |
| #42 | OrthoRF: Exploring Orthogonality in Object-Centric Representations | Despoina Touska, Bastiaan Onne Fagginger Auer, Alexandru Onose +6 | cs.CV | 2026-10-26 |
| #43 | Critic's Eye: Review-Grounded Graph Reasoning for Long-Form Motif Discovery | Xinyu Sun, Zhangyue Yin, Xinyi Ju +1 | cs.AI | 2026-10-26 |
| #44 | Checkpoint Reload Explains Most of the Measured State Gap in Two State Discovery Reproductions | Weijia Han, Lisha Qu | cs.LG | 2026-10-26 |
| #45 | Intervene, Calibrate, Discover: Learning Causal Structure from Pixels | Ziyi Ding, Xiaodi Huang, Xianxin Lai +4 | cs.AI | 2026-10-26 |
| #46 | RobotAgentBench: Towards Open-world Robot Autonomy | Lingjun Mao, Jinglin Cao, Lukun He +22 | cs.RO | 2026-10-26 |
| #47 | Data-driven Discovery of Lie Symmetries and First Integrals with Latent ODEs | Matt L. Wiemman, Peter Melchior | cs.LG | 2026-10-25 |
| #48 | Recovering Business Rules as Cascade Lookups for Enterprise Field Prediction | Changxu Duan | cs.LG | 2026-10-25 |
| #49 | Interpretable and Steerable Molecular Graph Generation using Concept Bottlenecks | Sarabeshwar Balaji, Ritesh Kumar, Lav R. Varshney | cs.LG | 2026-10-25 |
| #50 | Deep Scientific Reasoning under Physical Constraints: Structure-Aware Spectrum Prediction | Yingheng Wang, Tao Yu, Shufeng Kong +3 | cond-mat.mtrl-sci | 2026-10-25 |