| 1 | Taming the Agentic RAN: Stability-Guaranteed Arbitration of Autonomous AI Agents in O-RAN | Seyed Bagher Hashemi Natanzi, Bo Tang | cs.NI | 2026-09-16 |
| 2 | EviGen: Predictive Evidence Scaffolding for Verifiable Clinical Rationale Generation | Fengnan Li, Heman Burre, Liwen Sun +2 | cs.CL | 2026-09-16 |
| 3 | ReFigBench: Benchmarking Scientific Figure Reconstruction as Editable PowerPoint Artifacts | Liyang Fan, Chi Wei, Yitai Li +8 | cs.CL | 2026-09-16 |
| #4 | Using OCR Heads to Verbalize Image Semantics | Sheridan Feucht, Benno Krojer, Sarah Wang +3 | cs.CV | 2026-09-16 |
| #5 | CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents | Jiaxuan Jiang, Liyuan He, Zhixuan Fang | cs.AI | 2026-09-16 |
| #6 | FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection | Chengxian Hu, Zhiming Ma, Mingjun Pan +9 | cs.SD | 2026-09-16 |
| #7 | Clueing up LLMs with Tool-Augmented Deductive Reasoning | Rebecca Ansell, Autumn Toney-Wails | cs.AI | 2026-09-16 |
| #8 | "If I Had to Buy Just ONE: Galaxy S26 Ultra": Auditing AI-Generated Product Recommendations | Lucas G. Uberti-Bona Marin, Thales Bertaglia, Giovanni Astante +5 | cs.CY | 2026-09-16 |
| #9 | Mask IPL: Noise-Free Intrinsic Position Learning via Computation Graph Clipping for Event-Based Spike-Driven Tracking | Yimeng Shan, Malu Zhang | cs.CV | 2026-09-16 |
| #10 | Weakening Neurons: An Input-Output Functionality in Transformers with Outsize Influence | Sebastian Gerstner, Hilal AlQuabeh, Kentaro Inui +1 | cs.LG | 2026-09-16 |
| #11 | Hypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents | Izumi Takahara, Kazunori Nishio, Akira Aiba +4 | cond-mat.mtrl-sci | 2026-09-16 |
| #12 | Variational Quantum Transformer Architecture for Synthetic Language Generation | Julian Hager, Michael Kölle, Gerhard Stenzel +3 | quant-ph | 2026-09-16 |
| #13 | A Probe Shift Is Not a Fairness Fix: The Limits of Representation Steering in Speech Models | Nicolas Bourrel, Abderrahmane Issam, Gerasimos Spanakis | cs.CL | 2026-09-16 |
| #14 | Align, Integrate, and Fire: Efficient Token-Level Alignment for Zero-Shot SpeechLLMs | Abderrahmane Issam, Yusuf Can Semerci, Jan Scholtes +1 | cs.CL | 2026-09-16 |
| #15 | M-SQE: Multilingual Skill Quality Estimation for Enhancing Language Equality in Agentic Skill Use | Yilun Liu, Shimin Tao, Minggui He +9 | cs.CL | 2026-09-16 |
| #16 | Planning or Improvisation? Stress-Testing the Poetry Planning Site on Open Models and Open Cross-Layer Transcoders | Éric Jacopin | cs.CL | 2026-09-16 |
| #17 | MSR: Multiple Subject Reference for Video Generation | Guannan Li, Jiaji Chen, Jingyuan Liao +2 | cs.CV | 2026-09-16 |
| #18 | Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models | Shardul P. More, Tanuja S. Pawar | cs.CL | 2026-09-16 |
| #19 | What Counts as Strategic Reasoning? A Systematic Mapping of Chess Research on Humans, Engines, and Language Models | Paolo Ciancarini, Remo Pareschi | cs.AI | 2026-09-16 |
| #20 | Where Should Agents Live? Energy-Memory Characterization of Agentic AI for the Edge-Cloud Continuum | Carolina Fortuna, Vid Hanžel, Tim Strnad +1 | cs.AI | 2026-09-16 |
| #21 | Unified Response Geometry for Structured Pruning | Kaixiang Shu | cs.CV | 2026-09-16 |
| #22 | F-DACE: Fuzzy Disagreement-Aware Causal Evidence Fusion for Abstention-Safe Conversational Retail Decision Support | Sourish Dey | cs.LG | 2026-09-16 |
| #23 | A Lightweight CNN Integrated Compact Convolutional Transformer for Multi-Scale Feature Learning and reducing computational complexity for breast cancer mammography image detection and classification | Md Taimur Ahad, Ainuddin Ahmed | cs.LG | 2026-09-16 |
| #24 | WFM: Wiki Foundation Model for Complex Agentic Reasoning | Junnan Dong, Linhao Luo, Senlei Zhang +9 | cs.AI | 2026-09-16 |
| #25 | MoRE: Mixture of Reused Experts | Eric S. Qiu, Utku Umur Acikalin, Justin Lovelace +4 | cs.LG | 2026-09-16 |
| #26 | Reaching Every Position Without Searching: Rotating Sparse Wiring on the Hypercube as a Substitute for Attention | Yoshiaki Takashita | cs.LG | 2026-09-16 |
| #27 | Not All Layers Need Tuning: Diagnosing and Directing Adaptation in Vision-Language-Action Models | Shahram Najam Syed, Arthur Jakobsson, Prayuj Sachdev +1 | cs.RO | 2026-09-16 |
| #28 | Beyond Embedding Transfer: Component Roles in Grokking Transfer and Stability | Zeyu Jia | cs.LG | 2026-09-16 |
| #29 | vidax: A Unified JAX Framework for Video Generative Models on Accelerator Meshes | Congyue Deng | cs.CV | 2026-09-16 |
| #30 | The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction | Yu Lin, Yiming Wang, Runyuan Cai +2 | cs.AI | 2026-09-16 |
| #31 | Physics-Informed Neural Networks for Fast Multilayer Spectral Inversion of Hα 6562.8 A and Ca II 8542.1 A Spectra | Ziyang Zhang, Qin Li, Vasyl B. Yurchyshyn +4 | astro-ph.SR | 2026-09-16 |
| #32 | A Calibrated Instrument for Measuring How Inference Optimizations Affect Output Quality | Jerry Kaplan | cs.CL | 2026-09-16 |
| #33 | The Attention Within: Consensus Dynamics in Selective State Space Models | João Pedro Silvestre, Álvaro Rodríguez Abella, Paulo Tabuada | cs.LG | 2026-09-16 |
| #34 | TuiML: Machine Learning for AI Agents | Nilesh Verma, Nick Lim, Albert Bifet +1 | cs.AI | 2026-09-16 |
| #35 | Encoder Awakening via Adapters: Effective Domain-Adaptive Fine-tuning of Speech-LLMs | Mohan Shi, Zilai Wang, Natarajan Balaji Shankar +3 | eess.AS | 2026-09-16 |
| #36 | Mixed-Integer Nonlinear Differentiable Predictive Control for Underground Pumped Hydro Energy Storage Systems | Honghui Zheng, Ján Boldocký, Yury Dvorkin +1 | eess.SY | 2026-09-16 |
| #37 | Maximum Strong Independent Sets in Hypergraphs: Reductions, Bounds, and Greedy Certificates | Yingquan, Wu, Jason Cong | cs.LG | 2026-09-16 |
| #38 | ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference | Amir Ziashahabi, Hossein Entezari Zarch, Lei Gao +2 | cs.LG | 2026-09-16 |
| #39 | Beyond the Previous Layer: Residual Predictive Structure in Sparse MoE Routing | Hao Li, Yasuyuki Tahara, Yuichi Sei | cs.LG | 2026-09-15 |
| #40 | Long-Context Demonstration Selection Using State Space Models | Ziniu Zhang, Zhenshuo Zhang, Ruoxuan Xiong +2 | cs.LG | 2026-09-15 |
| #41 | Investigating Adversarial Robustness of Heterogeneous Cooperative Perception | Chenyi Wang, Yutong Liu, Qingzhao Zhang +1 | cs.CV | 2026-09-15 |
| #42 | AfriSyCo: Measuring Assertive Framing, Verification, and Wording Sensitivity Around African-Language Content | David Ababio Awuni, Rose-Mary Owusuaa Mensah Gyening, Elvis Gyasi Owusu | cs.CL | 2026-09-15 |
| #43 | Procedural Pretraining for Molecular Property Prediction | Moritz Friedemann, Zachary Shinnick, Philip Torr +1 | cs.LG | 2026-09-15 |
| #44 | NObSP: Functional Decomposition of Neural Networks via Oblique Subspace Projections | Alexander Caicedo, Víctor De La Hoz, Santiago Alférez | cs.LG | 2026-09-15 |
| #45 | A Four-Stage Decomposition of Word-Problem Solving and Mechanistic Fragility in LLM Math Reasoning | Zhongdi Qu, Carla P. Gomes | cs.AI | 2026-09-15 |
| #46 | FairCompressAgent: An Agentic Framework for Fairness-Aware Model Compression for FPGA Deployment | Yuanbo Guo, Yiyu Shi | cs.AI | 2026-09-15 |
| #47 | CALOS: Control-Affine Lyapunov On-manifold Safety Layer for Safe Deep Reinforcement Learning for Quadrotors | Fabrizio Cesareo, Sebastiano Mengozzi, Nicola Mimmo +1 | cs.RO | 2026-09-15 |
| #48 | Agentic Societies Need a Social Harness | Tapan Chugh, Vidushi Singh, Krish Jain +2 | cs.MA | 2026-09-15 |
| #49 | LACE: Layer-Wise Compression for Dynamic Frame Rate Codecs | Thanapat Trachu, Samuele Cornell, William Chen +1 | cs.SD | 2026-09-15 |
| #50 | FreqSpaNet: Frequency and Spatial Learning of SFPF for Physical Layer Hardware Integrity Detection | Xiaoxuan Huang, Jinlong Xu, YiZhe Wang +3 | cs.LG | 2026-09-15 |