| 1 | RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing | Yilun Hao, Krishna Sayana, Isabella Ye +4 | cs.AI | 2026-10-07 |
| 2 | Validity Without Ground Truth: What Stated-Preference Economics Offers the Evaluation of Language Models | Daniel Robert Kling Alexander, Catherine Louise Kling | cs.AI | 2026-10-07 |
| 3 | NeuralBES: A Differentiable, Control-Aware Emulator for Scalable Building Energy Modeling | Ting-Yu Dai, Takuya Kurihana, Wing Yee Au +1 | cs.LG | 2026-10-07 |
| #4 | OrBIT: Structure-Guided Embedding Compression | Yunied Puig, Amit Kumar Jaiswal | cs.LG | 2026-10-07 |
| #5 | Temporally Interpretable Differentiable Decision Trees | Eisuke Hirota, Aarav Sane, Rohan Paleja | cs.LG | 2026-10-07 |
| #6 | ORDERS: An Empirical Study of Norm-Rank Aggregation for Personalized Federated Learning | Koffka Khan | cs.LG | 2026-10-07 |
| #7 | Conformal Prediction for Spatially Dependent Data via Sequential Whitening | Ayush Baran Sen, Arkajyoti Saha | stat.ML | 2026-10-07 |
| #8 | HarnessIR: Harnessing Multimodal Foundation Models for Universal Real-World Image Restoration | Xiangtao Kong, Shuaizheng Liu, Rongyuan Wu +5 | cs.CV | 2026-10-07 |
| #9 | Structure alone supports efficient visual computation in the Drosophila visual system | Eudald Correig-Fraga, Roger Guimerà, Marta Sales-Pardo | q-bio.NC | 2026-10-07 |
| #10 | Temporal Predictive Multiplicity: Equally Accurate Time Series Models Yield Different Forecast Trajectories | Emanuele Albini, Francesca Toni, Saumitra Mishra +1 | cs.LG | 2026-10-07 |
| #11 | Marrying Pricing and Advertising with LLMs | Alessandro Barro, Francesco Bacchiocchi, Francesco Emanuele Stradi +1 | cs.GT | 2026-10-07 |
| #12 | Expected Sample Complexity in Multi-Armed Bandits | Nadav Sukenik, Nadav Merlis | cs.LG | 2026-10-07 |
| #13 | AdaPS-LiNGAM: Adaptive Predecessor Selection for Linear Non-Gaussian Acyclic Models under Small-Sample Settings | Shun Yanashima, Kentaro Kanamori, Hirofumi Suzuki | cs.LG | 2026-10-07 |
| #14 | Reproducible LLM Inference Benchmarking: A Sequential Isolation Protocol for Regression Testing | Arnold Olympio, Juan Manuel Servera Bondroit, Wael Abdelmalek +2 | cs.PF | 2026-10-07 |
| #15 | Latent Watermarks under Generative Editing: A Benchmark and Analysis of Detection Survival | Sung Ju Lee, Nam Ik Cho | cs.CV | 2026-10-07 |
| #16 | When Rank Rises as LLMs Degrade | Zhaohui Geoffrey Wang | cs.LG | 2026-10-07 |
| #17 | Quantum anomaly detection in real scarce data | Emanuele Casciaro, Fabio Mascherpa, Alfonso Amendola +1 | quant-ph | 2026-10-07 |
| #18 | Coding-Agent Benchmarks Should Match Their Users' Task Flows | Igor Slinko, Yaroslav Golubev, Sergey Titov | cs.LG | 2026-10-07 |
| #19 | Sequential Pretraining Favors Large Models | Mohnish Harwani, Yujia Zheng | cs.LG | 2026-10-07 |
| #20 | When Should an In-Context Learner Expand Its Hypothesis Space? | Weihan Li, Xinlei Chen, Junhao Wu +1 | cs.LG | 2026-10-07 |
| #21 | Constrained Diffusion for Data-Scarce Orbital Monte Carlo in Constellation Tasking | Omar Ramadan, Sam Siavoshian, Amir Kashif Saeed +3 | astro-ph.IM | 2026-10-07 |
| #22 | FLoRa: Flight-Assisted Data Collection from Duty Cycling LoRa Nodes under Energy Constraints | Naresh Babu Kakarla, V. Mahendran | cs.NI | 2026-10-06 |
| #23 | Lower Bounds for Parallel Diffusion Sampling | Yiwen Kou, Yimeng Wang | cs.DS | 2026-10-06 |
| #24 | Spatial Induction Heads: In-Context Learning of Multidimensional Cellular Automata | Kimia Kazemian, Menghan Xu, John Thickstun +1 | cs.LG | 2026-10-06 |
| #25 | Convex-Concave Reinforcement Learning | Shripad V. Deshmukh, Yaswanth Chittepu, Dhawal Gupta +2 | cs.LG | 2026-10-06 |
| #26 | Multi-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled Autonomous Agents | Nikolaos Kekatos, Dimitrios Nikou, Anastasios Temperekidis +4 | cs.CR | 2026-10-06 |
| #27 | CARE: Certifying Acceleration for Vision-Language-Action Inference | Rui Liu, Tong Zheng, Jindong Gu +1 | cs.CL | 2026-10-06 |
| #28 | Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems | Tunyu Zhang, Zihao Zhao, Yusong Zhao +5 | cs.AI | 2026-10-06 |
| #29 | Reinforcement Learning with Conformal Action Sets: An Application to Sequential Recommendation | Wenwen Si, Honghao Wei | cs.LG | 2026-10-06 |
| #30 | ScienceClaw: Benchmarking Continual Self-Evolution of AI-for-Science Agents Across the Natural and Social Sciences | Mingda Zhang, Wenjin Liu, Tiesunlong Shen +6 | cs.AI | 2026-10-06 |
| #31 | Steering Diffusion Models to Rare Events with Sequential Monte Carlo | Aavash Subedi, Tim Reichelt, Christopher Williams +3 | stat.ML | 2026-10-06 |
| #32 | SquidAgent: Parallelize Wisely, Coordinate Efficiently | Yexiong Lin, Shanshan Ye, Yu Yao +3 | cs.AI | 2026-10-06 |
| #33 | Parallel Predictive World Models for Accurate and Efficient Long-Horizon Planning | Wanjin Feng, Baobin Zhang, Ao Yu +3 | cs.AI | 2026-10-06 |
| #34 | DeltaTTT: Layerwise Optimization for Nonlinear Recurrent Memory | Yining Li, Dongchen Han, Jie Fu +1 | cs.LG | 2026-10-06 |
| #35 | How Much Planning Is Enough? Reducing Search and Computation in World-Model Planning | Changbai Li, Sirui Li, Yichen Yang +4 | cs.RO | 2026-10-06 |
| #36 | Catastrophic Forgetting in Sequential Thermal Anti-UAV Detection: The Role of Scale-Conditioned Gradient Imbalance | Khac Duc Giang Nguyen, Seyed Sahand Mohammadi Ziabari, Ali Mohammed Mansoor Alsahag | cs.CV | 2026-10-06 |
| #37 | CoDe-LoRA: Mitigating the Orthogonality Dilemma in Continual Learning of LLMs via Knowledge Consolidation and Decoupling | Maoqi Liu, Quan Fang, Yufei He | cs.AI | 2026-10-06 |
| #38 | Anytime-valid simulation-based hypothesis testing | Patrick Forré, Lydia Brenner | stat.ML | 2026-10-06 |
| #39 | SpeedrunBench: Challenging LLM Agents with Video Game Speedrunning | Yoshinari Fujinuma, Keisuke Kamahori, Ryuto Koike +8 | cs.AI | 2026-10-06 |
| #40 | Confidence Reasoning Graphs: Structured Confidence Estimation for LLM Agents | Brendan King, Farima Fatahi Bayat, Jean-Flavien Bussotti +2 | cs.AI | 2026-10-06 |
| #41 | Adapting Vision-Language-Action Models to Unknown Visual Disruptions During Execution | Ahin Lee, Jinwoo Seo, Youngsoo Jang +1 | cs.RO | 2026-10-06 |
| #42 | Isotropic Yet Undecodable: The Sequential Content-Sufficiency Gap in Latent-Predictive Text Representations | K. P. Santoso, N. Z. Fadil, F. P. Harsanti +2 | cs.AI | 2026-10-06 |
| #43 | Learned Adaptive Multiresolution Diffusion Imaging | Christian Tantardini, Stig Rune Jensen, Roberto Di Remigio Eikås +1 | math.NA | 2026-10-06 |
| #44 | Self-Referenced Social Preferences: Cooperation without Observing Others Rewards | Mohamed Ayman Mohamed, Harshil Kotamreddy, Marcos Menon Jose | cs.AI | 2026-10-06 |
| #45 | Tram-FL: Reducing Communication and Computation Costs through Sequential Model Circulation in Decentralized Federated Learning | Kota Maejima, Takayuki Nishio, Asato Yamazaki +1 | cs.LG | 2026-10-06 |
| #46 | Do I Need the Cloud? Uncertainty-Aware Step-Level Handoff for Small Language Model Agents | Abolfazl Younesi | cs.AI | 2026-10-06 |
| #47 | From Evidence to Action: How Tool-Using Agents Fail | Hongzhan Lin, Shidong Cao, Ziyang Luo +3 | cs.CL | 2026-10-06 |
| #48 | Detecting LLM-Assisted Vietnamese Writing via Keystrokes under Behavioral Manipulation | Thanh Dong, An Ngo, Minh Dau +1 | cs.CL | 2026-10-06 |
| #49 | EIO-Agents: The Missing Semantic Layer for AI Agent Evaluation | Fouad Bousetouane | cs.AI | 2026-10-06 |
| #50 | Learning to Outgrow a Theory: Experimental Discovery Beyond the Initial Hypothesis Space | SiYuan Ma, Albert Gao, Chunzheng Zhu +6 | cs.AI | 2026-10-06 |