| 1 | VeriCUA: Verification as Agentic Exploration for Computer-Using Agents | Qiushi Sun, Da Yu, Alexander Knop +5 | cs.AI | 2026-10-29 |
| 2 | LatentWeave: Test-Time Latent Optimization for Multimodal Reasoning | Fanci Meng, Kun Wang, Guibin Zhang +4 | cs.LG | 2026-10-29 |
| 3 | Agent-Wise Test-Time Normalization for Camera-Based Cooperative Perception with Corrupted Collaborators | Yu Wang, Shaohua Wang, Yicheng Li +1 | cs.CV | 2026-10-29 |
| #4 | Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute? | Qi Wang, Yun Qu, Lizhou Cai +10 | cs.AI | 2026-10-29 |
| #5 | Timbre: Reliability-aware harmonic consensus for label-free multimodal test-time rexinforcement learning | Haotian Lyu, Haoyu Wang, Ru Wang +4 | cs.AI | 2026-10-29 |
| #6 | Generating Critic-Guided Synthetic Experience in Latent World Models | Jorge de Freitas, Christos Ziakas, Alessandra Russo | cs.LG | 2026-10-29 |
| #7 | Certified Access: Test-Time Compute on Conservative Physics-Structured AI Memory | Pratik Jawahar, Riccardo Maggioni, Jonas Petersen +5 | cs.AI | 2026-10-29 |
| #8 | Blind Spots: Where Small Language Models Fall Behind Frontier Models on Terminal Tasks | Ashima Suvarna, Ruta Desai, Ahmed Elgohary | cs.CL | 2026-10-28 |
| #9 | AtomSteer: Test-Time Constraint Steering for Atomistic Generative Models | Pengfei Cai, Katharina S. C. Jäger, Utkarsh Utkarsh +4 | cs.LG | 2026-10-28 |
| #10 | Calibrating Track-Query Updates at Test Time for Multi-Object Tracking | Riku Inoue, Shogo Sato, Yu Mitsuzumi +3 | cs.CV | 2026-10-28 |
| #11 | Compute Has Shape: Self-Morphing the Internal Computation of Frozen LLMs | Junxi Wu, Yiwen Guo, Shu-Tao Xia | cs.AI | 2026-10-28 |
| #12 | Encode Once, Answer Many: Internalizing Context via Parametric Flow | Xinhao Zhong, Mengxuan Wu, Chonghua Liao +22 | cs.AI | 2026-10-28 |
| #13 | Aligning Misaligned Benchmarks for Single-View Novel View Synthesis | Yang-Che Tseng, Erqun Dong, Jeong-gi Kwak +5 | cs.CV | 2026-10-28 |
| #14 | ParaTTT: Parallelizing Test-Time Training Layers with Deep Memories | Noel Loo, Neehal Tumma, T. Konstantin Rusch +3 | cs.LG | 2026-10-28 |
| #15 | Rubricon: Automated Rubric Generation and Refinement for LLM Evaluation and Training | Ulyana Tkachenko, Hui Wen Goh, Guram Gogia +1 | cs.AI | 2026-10-28 |
| #16 | What Does LOL Measure? Hidden Label Shifts in Low-Light Enhancement Benchmarks | Adityan Thirumani Srinivasan | cs.CV | 2026-10-28 |
| #17 | Nemotron 3.5 Super and Lightning: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Models for Agentic AI | NVIDIA, :, Aastha Jhunjhunwala +556 | cs.CL | 2026-10-28 |
| #18 | Meta-Initialization of Implicit Neural Representations to Accelerate Deformable Medical Image Registration | Marat O. Zinovev, Dmitry V. Sorokin | cs.CV | 2026-10-27 |
| #19 | FAD-KV: Adaptive Dictionary KV Caching for Efficient Reasoning Decoding | Yuxuan Zhu, David H. Yang, Parisa Shiravani +5 | cs.CL | 2026-10-27 |
| #20 | When Should We Intervene at Test Time? | Jiahao Zhang, Xinling Wen, Liangliang Li +1 | cs.LG | 2026-10-27 |
| #21 | Test-Time Communication in Trading Agent Swarms | Avid Fayaz, Harry Zhang, Håvard Alstadheim +3 | cs.MA | 2026-10-27 |
| #22 | Representing the Unseen: Rethinking Visual Imagination for Spatial Reasoning | Zengqi Zhao, Zun Wang, Shoubin Yu +2 | cs.CV | 2026-10-27 |
| #23 | TopoField: Technical Report for ECCV 2026 SceneFun3D Challenge | Zhiwei Chen, Zhiheng Fu, Zixu Li +3 | cs.CV | 2026-10-27 |
| #24 | Retrieve to Act: Motion Primitive Graph Retrieval for Robust VLA Execution | Pham Tri Quang, Bao-Ngoc Dao, Minh Duc Nguyen +15 | cs.RO | 2026-10-27 |
| #25 | How Much Can Best-of-N Help a World Action Model? Measuring Selectable Headroom and Realizing It in Closed Loop | Haojia Gao, Yue Cao, Yumin Liu +6 | cs.RO | 2026-10-27 |
| #26 | Tail Cues, Principal Corrections: Plug-and-Play Rectification for Open-Set Test-Time Adaptation | Yingkai Yang, Chaoqi Chen, Hui Huang | cs.LG | 2026-10-27 |
| #27 | Select-TTT: Query-Conditioned Selective Fast Weight Updates for In-Place Test-Time Training | Yue Wu, Yang Zhang, Weinan Gan +4 | cs.LG | 2026-10-27 |
| #28 | The Batch Size Can Be One: Test-Time Adaptation from Classifier Geometry | Jaeho Hwang, Yujin Oh, Juhyeon Shin +3 | cs.LG | 2026-10-27 |
| #29 | Diagnosing and Correcting Bias in MLLM for Long Video Understanding | Xusheng Liang, Jianqiao Sun, Hao Zhang +3 | cs.CV | 2026-10-26 |
| #30 | Beyond Update Counts: A Control Map for Evaluating Test-Time Model Updates | Zehao Zhao, Shangjian Yin, Rui Liu +6 | cs.LG | 2026-10-26 |
| #31 | Closed-Loop Aware Planning via Imitation-Free Speed Scoring for End-to-End Autonomous Driving | Emad Aghajanzadeh, Thomas Schwarzfischer, Marc Kaufeld +8 | cs.RO | 2026-10-26 |
| #32 | Rollback: Experience Backtracking in World Models for Policy Improvement | Jiayi Luo, Yang Zhang, Liliang Chen +13 | cs.RO | 2026-10-26 |
| #33 | Adapt for Planning, Not just Prediction: Optimistic Test-Time World Model Adaptation | Akshay Mete, Dileep Kalathil, P. R. Kumar | cs.LG | 2026-10-26 |
| #34 | Test-Time Confidence Adaptation under RL-Induced Trajectory Shift | Zhenzhen Ren, Xiaoqing Zhang, GuoBiao Li +4 | cs.AI | 2026-10-26 |
| #35 | Test-Time Prompt-Agnostic Decomposition | Junze Wang, Lei Fan, Dezheng Zhang +4 | cs.CV | 2026-10-26 |
| #36 | A Certified Robustness Framework for Backdoor Poisoning Attacks using $f$-Divergences | Evan Rose, Alina Oprea | cs.LG | 2026-10-26 |
| #37 | Supervising the Visible State: Separating Representation from View Selection in Streaming Video | Yihao Hu, Pan Wang, Yitong Lin +8 | cs.CV | 2026-10-26 |
| #38 | Recovering Black-Box Point Cloud Models from Pose Shifts via Derivative-Free Optimization | Seonghwan Park, Min-Gyu Park | cs.CV | 2026-10-26 |
| #39 | Efficient Multi-modal Video Fusion Network with Dynamic Region-Guided Temporal Interaction | Jingxue Huang, Xiaosong Li, Yi Lin | cs.CV | 2026-10-26 |
| #40 | Rethinking Verification in Agent Harnesses | Zhengxin Zhang, Erkang Zhu, Yin Lin +3 | cs.AI | 2026-10-25 |
| #41 | CaliMem: Search-Efficient Data Agent via Calibrated Memory | Hanze Li, Athan Z. Li, Feiyang Kang +4 | cs.AI | 2026-10-25 |
| #42 | EvolveMAS: A Unified Self-Evolution Framework for Decentralized Multi-Agent Systems | Yalun Wu, Qiwei Ma, Bingbing Xu +10 | cs.MA | 2026-10-25 |
| #43 | h1: A Taste of the Bitter Lesson in Automated Theorem Proving | Skander Moalla, Ahmad Rammal, Niket Patel +2 | cs.LG | 2026-10-25 |
| #44 | TurboWAM: Learning What Matters for Fast World Action Models | Guile Wu, Shuangzhi Li, Xingxin Chen +5 | cs.CV | 2026-10-24 |
| #45 | Counterfactual Test-Time Augmentation for Shortcut Removal in Language Models | Katie Matton, Rosalind W. Picard, John Guttag +1 | cs.LG | 2026-10-24 |
| #46 | More: Mode-Optimized Reasoning with Self-Adaptive Effort for Self-Evolving Agents | Dianxing Shi, Dingjie Fu, Tianyu Lei +1 | cs.AI | 2026-10-24 |
| #47 | SkillShift-Bench: Benchmarking Skill Learning under Environment Evolution for Web Agents | Bo-Yu Chen, Zhi Zhou, Yu-Feng Li | cs.AI | 2026-10-24 |
| #48 | ActionRAG: Evidence-Refining Graph Diffusion for Long-Term Memory in LLM Agents | Navyansh Mahla, Sashank Vandrangi | cs.AI | 2026-10-23 |
| #49 | Cross-Architectural Feature Fusion for Coronary Artery Stenosis Detection in X-ray Angiography | Haobo Zhu, Mojtaba Lashgari, Jason Chai +3 | cs.CV | 2026-10-23 |
| #50 | When is more search useful? An Empirical Study of Search Utility in Quality-Aware Decoding for Machine Translation | Javier Garcia Gilabert, Rico Sennrich, André F. T. Martins | cs.CL | 2026-10-23 |