| 1 | Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency | Parsa Hosseini, Akasha Tigalappanavara, Sumit Nawathe +6 | cs.AI | 2026-09-25 |
| 2 | User Model Extraction via Belief Self-Distillation | Ali Holmov, Yiran Huang, Kirill Bykov +1 | cs.LG | 2026-09-25 |
| 3 | How Far Can INRs Go? Cross-Domain Parameter-efficient INR-Based Semantic Segmentation for Brain MRI | Ziyao Shang, Pouya Sadeghi, Letian Jiang +2 | cs.CV | 2026-09-25 |
| #4 | Multi-agent Scaling Across Disjunctive and Compensatory Tasks | Carolina Fortuna, Blaz Bertalanic | cs.AI | 2026-09-25 |
| #5 | Generalization behavior of OPTQ and the role of regularization | Erin George, Rayan Saab | cs.LG | 2026-09-25 |
| #6 | HySTAR: Anchored Hypergraphs for Stable Credit Assignment in Cooperative Multi-Agent Reinforcement Learning | Xinglong Luo, Yuding Zhang, Yuheng Kuang +5 | cs.LG | 2026-09-25 |
| #7 | Prompt Minimization: Reducing Input Redundancy Without Sacrificing Output Fidelity | Marius F. R. Juston, Kevin A. Karim, Jonathan Gao +2 | cs.AI | 2026-09-25 |
| #8 | Diagnosing the Sources of Compositional Failure in Vision-Language Models: A Controlled Analysis | Mona Gandhi, Cenk Merih Olcay, Kuan-Chieh Lo +3 | cs.CV | 2026-09-25 |
| #9 | From Reward Signal to Visual Utility: A Controlled Audit of Medical VLM Post-Training | Wang Jingxin | cs.CV | 2026-09-25 |
| #10 | Compress What You See, Not What You Say: Anchored Context Distillation for Latent-Observation Software Engineering Agents | Zhensheng Zou, Guoqing Wang, Dan Hao | cs.AI | 2026-09-25 |
| #11 | Sorry Robot, Happy Human: Vision-Language Models Read Only One of Two Legible Typographic Layers | Mert İncidelen, Yamen Kashkash, Asya Berker +1 | cs.CL | 2026-09-25 |
| #12 | Guiding End-to-End Driving Models with Endpoint-Constrained Trajectory Optimization | Brayden Zhang, Mahsa Golchoubian, Igor Gilitschenski +2 | cs.RO | 2026-09-25 |
| #13 | Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding | Zhaoyuan Xia, Qinghongbing Xie, Yung Xiang Hue +7 | cs.CL | 2026-09-25 |
| #14 | LUCID: Learning Under Confounding for Inference and Discovery in Time Series | Mohammad Fesanghary | cs.LG | 2026-09-25 |
| #15 | Towards VLA-Dreamer: Refining VLA Behavior Using World Models | Parsa Mastouri Kashani, Jan-Gerrit Habekost, Stefan Wermter | cs.RO | 2026-09-25 |
| #16 | G2MAF: Test-Time Gradient Guidance for Multi-Agent Flow Policies | Guowei Zou, Haitao Wang, Guoxin Wang +4 | cs.AI | 2026-09-25 |
| #17 | Acoustic-to-Text KV Compression for Full-Duplex Speech Models | Yejin Lee, Seungbeom Kim, Yongha Lee +1 | cs.SD | 2026-09-25 |
| #18 | Which Influence Are We Estimating? The Role of Counterfactual Specifications in Data Attribution | Zhe Li, Wei Zhao, Peixin Zhang +1 | cs.AI | 2026-09-25 |
| #19 | Light Field Primitive for Novel View Synthesis | Liang Chen, Jiahui Ning, Xun Jiang +4 | cs.CV | 2026-09-25 |
| #20 | Rethinking Data Quality for AI-Driven Systems: Evidence from Practitioner Interviews | Hariharan Gopinath, Jan Bosch, Helena Holmström Olsson | cs.SE | 2026-09-25 |
| #21 | SPO: Discovering Adaptive Large Neighborhood Search Operators via Stackelberg Program Optimization | Xinyi Ke, Kai Li, Junliang Xing +2 | cs.AI | 2026-09-25 |
| #22 | Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability? | Ziyi Wang, Li Li, Aolin Zhou +4 | cs.AI | 2026-09-25 |
| #23 | Monitor Jailbreaking: Evading Chain-of-Thought Monitoring Without Encoded Reasoning | Julian Schulz | cs.AI | 2026-09-25 |
| #24 | Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods | Saksham Kiroriwal, Julius Pfrommer, Jürgen Beyerer | cs.LG | 2026-09-25 |
| #25 | Neuralyzing the Trace: Selective Representation-Level Unlearning with Contrastive Sparse Autoencoders | Itai Zehavi, Fanny Jourdan, Ulrich Aivodji | cs.AI | 2026-09-25 |
| #26 | Cheap, open agents make LLM pollution harder to mitigate | Raluca Rilla, Anne-Marie Nussberger, Rui Mata +1 | cs.AI | 2026-09-25 |
| #27 | KuaFu: Compressing Long User Behavior into Understanding at Billion Scale | Jiahao Hui, Lin Zhu, Yishen Hu +8 | cs.IR | 2026-09-25 |
| #28 | FLIP: Final Layer Inference-Time Probing for Vision-Language Models | Drandreb Earl O. Juanico, Rowel O. Atienza | cs.CV | 2026-09-25 |
| #29 | Evaluating Sycophancy in Chinese Large Language Models on Factual Questions Derived from Online Search Queries | Geng Liu, Feng Li, Mengxiao Zhu +1 | cs.CL | 2026-09-25 |
| #30 | MoMHa: Multi-Objective Optimization of LLM Harnesses over Accuracy, Safety, and Tokens | Subhojyoti Mukherjee, Md Mehrab Tanjim | cs.AI | 2026-09-25 |
| #31 | PORL: Pretrained Offline Reinforcement Learning for the Job Shop Scheduling Problem | Mateo Toro Diz, Jonathan Hoss, Noah Klarmann | cs.LG | 2026-09-25 |
| #32 | Financial Fragility in Societies of LLM Agents: Coordination Failures and Stabilizing Mechanisms | Zhenhao Fu, Ruipeng Xu, Qibing Ren | cs.AI | 2026-09-25 |
| #33 | MACBT: A Multi-Agent Cognitive Behavioral Therapy Decision Support System with Longitudinal Memory | De Jiang, Shuo Zhang, Weiwei Liao +4 | cs.AI | 2026-09-25 |
| #34 | Robust to Which Model Change? A Unified Evaluation of Robust Counterfactual Explanations | Marcin Kostrzewa, Maciej Zięba | cs.LG | 2026-09-25 |
| #35 | CacheReforge: Bounded Recovery for Stale KV Caches under Evolving Adapters | Yuhang Cao, Yanzhou Mu, Chunrong Fang +1 | cs.LG | 2026-09-25 |
| #36 | SkillEvoReg: Regularizing Agent Skill Evolution Against Overfitting | Guanyu Nie, Fangzhou Zhu, Shixiong Kai +3 | cs.AI | 2026-09-25 |
| #37 | Learning Chance-Constrained MDPs with Bellman Distributional Certificates | Chenbei Lu, Hongyu Yi | cs.LG | 2026-09-25 |
| #38 | Peer-Grounded Counterfactual Path Planning for Chronic Health Management | Saman Khamesian, Hassan Ghasemzadeh | cs.LG | 2026-09-25 |
| #39 | Evaluation Is All You Need for Multi-Modal Autonomous Driving | Zeyu He, Shiqi Liu, Ke Chen +14 | cs.RO | 2026-09-25 |
| #40 | Motion Style Slider: Endpoint-Supervised Continuous Style Control for Human Motion Diffusion | Chen-Chieh Liao, Yichen Peng, Yiyi Cai +5 | cs.CV | 2026-09-25 |
| #41 | Towards Universal Representation-Based Process Control | Jinmyeong Choi, Taesup Kim, Artur Dubrawski | cs.LG | 2026-09-25 |
| #42 | Learning Natural Conversational Behavior in Tandem Speech-to-Speech Models with Randomized Guidance | Manato Yaguchi, Yotaro Kubo, Hikaru Asano +1 | cs.CL | 2026-09-25 |
| #43 | From S3Q Theory to Implementation: Towards an Architecture for Machine Qualia | Tetiana Grinberg, Katrina Schleisman, Patryk Laurent +6 | cs.AI | 2026-09-25 |
| #44 | Analyzing and Mitigating Cost-Inefficient Behaviors in Coding Agents | Yiran Hu, Nan Jiang, Shanchao Liang +3 | cs.AI | 2026-09-25 |
| #45 | TrafficImag: A Benchmark for Counterfactual Roadside Traffic Video Generation | Xiangyu Li, Tianyi Wang, Zhihao Dou +2 | cs.CV | 2026-09-25 |
| #46 | Words Speak Louder Than Order: A Behavioral Evaluation of Gemma 4 | Amanda Fitch | cs.CL | 2026-09-25 |
| #47 | TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding | Yibo Ma, Qianqian Zhang, Peng Liu +1 | cs.CL | 2026-09-25 |
| #48 | Prompt Injection Detection for Email Agents Through Attack Chain Modeling | Ahmad Hashmi, Dhyey Patel, Yunting Yin | cs.CR | 2026-09-25 |
| #49 | LLM Agents Can Easily Tamper With Their Own Traces | Jeremy Qin, David Schmotz, Derck Prinzhorn +3 | cs.CR | 2026-09-24 |
| #50 | JevOut: Natural Context Can Flip Decision Models | Zixiang Xu | cs.CL | 2026-09-24 |