| IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model IdentifierarXiv:2609.10494cs.CL | Blake Stenstrom, Charangan Vasantharajan, Brian Sathianathan | — | 11 Sept 2026 | — | — | — | — |
| Show-Harness: Just a VLM Agent Can Play RobotsarXiv:2609.10522cs.RO | Yanzhe Chen, Zechen Bai, Zhijun Cao +2 | — | 11 Sept 2026 | — | — | — | — |
| Reinforcement Learning with Temporal-Logic-Based Causal DiagramsarXiv:2306.13732cs.AI | Yash Paliwal, Rajarshi Roy, Jean-Rapha\"el Gaglione +2 | — | 11 Sept 2026 | — | — | — | — |
| Reinforcement learning for Quantum Tiq-Taq-ToearXiv:2411.06429cs.AI | Catalin-Viorel Dinu, Thomas Moerland | — | 11 Sept 2026 | — | — | — | — |
| ROTATE: Regret-driven Open-ended Training for Ad Hoc TeamworkarXiv:2505.23686cs.AI | Caroline Wang, Arrasy Rahman, Benjamin Nativi +2 | — | 11 Sept 2026 | — | — | — | — |
| RelayS2S: A Dual-Path Speculative Generation for Real-Time DialoguearXiv:2603.23346cs.AI | Long Mai, Junli Liang | — | 11 Sept 2026 | — | — | — | — |
| MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory PredictionarXiv:2604.10169cs.AI | Wenchang Duan, Zhenguo Gao, Jinguo Xian +1 | — | 11 Sept 2026 | — | — | — | — |
| Zero-shot World Models Are Developmentally Efficient LearnersarXiv:2604.10333cs.AI | Khai Loong Aw, Klemen Kotar, Wanhee Lee +2 | — | 11 Sept 2026 | — | — | — | — |
| Non-Stationarity Breaks Permutation Surrogates in Multi-Agent Reinforcement Learning: Diagnosis and RemediesarXiv:2604.23716cs.AI | Nikolaos Al. Papadopoulos, Konstantinos E. Psannis | — | 11 Sept 2026 | — | — | — | — |
| CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website ClassificationarXiv:2604.25512cs.AI | Mainak Sen, Kumar Sankar Ray, Amlan Chakrabarti | — | 11 Sept 2026 | — | — | — | — |
| Grounded Continuation: A Linear-Time Runtime Verifier for LLM ConversationsarXiv:2605.14175cs.AI | Qisong He, Jinwei Hu, Xinmiao Huang +2 | — | 11 Sept 2026 | — | — | — | — |
| Cultural Binding Heads in Language ModelsarXiv:2605.28543cs.AI | Avrile Floro, Luca Benedetto | — | 11 Sept 2026 | — | — | — | — |
| KairosAgent: Agentic Time Series Forecasting with Fused Semantic ReasoningarXiv:2605.30002cs.AI | Kun Feng, Ziwei Shan, Yuchen Fang +2 | — | 11 Sept 2026 | — | — | — | — |
| Self-Evolving Scientific Agent Designs Physically Reasoned White-Box Fluid ControlarXiv:2606.08405cs.AI | Boai Sun, Wenjin Guo, Zongmin Yu +1 | — | 11 Sept 2026 | — | — | — | — |
| KernelGenBench: Can LLMs and Agents Write Efficient Kernels Across Operator Sources and Hardware Platforms?arXiv:2607.27231cs.AI | Peiyu Zang, Jian Tao, Jialing Zhang +2 | — | 11 Sept 2026 | — | — | — | — |
| ViSR-KGC: Visual Subgraph Reasoning with Vision-Language Models for Multimodal Knowledge Graph CompletionarXiv:2608.05833cs.AI | Jiafan Li, Mengxue Yang, Jiaqi Zhu +2 | — | 11 Sept 2026 | — | — | — | — |
| Learning to Predict Middle-Layer Attention in MLLMs for Visual Token PruningarXiv:2608.06411cs.AI | Yuyao Sun, Tao Deng, Shuang Li +2 | — | 11 Sept 2026 | — | — | — | — |
| LiFTER: A Grounded Neuro-Symbolic Microscope for Continuous-Time Dynamic Graph ForecastingarXiv:2608.06765cs.AI | Minwoo Yu, Young-guk Ha | — | 11 Sept 2026 | — | — | — | — |
| A Human Audit of OpenAIs AI-Generated Mathematical ProofsarXiv:2608.14673cs.AI | Miko{\l}aj Sienicki, Krzysztof Sienicki | — | 11 Sept 2026 | — | — | — | — |
| Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and RecommendationarXiv:2608.15877cs.AI | Rui Wang, Jiazhou Wang, Zheng Wei +2 | — | 11 Sept 2026 | — | — | — | — |
| Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI AgentsarXiv:2608.16578cs.AI | Batu El, Jinhee Paeng, Fatih Dinc +2 | — | 11 Sept 2026 | — | — | — | — |
| FrontierChallenge: Evaluating Scientific Workflow CompletionarXiv:2608.24979cs.AI | Liangcai Su, Zhaopeng Feng, Zhuo Chen +2 | — | 11 Sept 2026 | — | — | — | — |
| A Composable Evaluation System for Reproducible Omni-Modal Foundation Model EvaluationarXiv:2609.01315cs.AI | Hodong Lee, Sanghee Park, Dohoon Ryu +2 | — | 11 Sept 2026 | — | — | — | — |
| Beyond Prompts: Measuring and Optimizing LLM Tool-Agent HarnessesarXiv:2609.05736cs.AI | Cen Mia Zhao, Haibo Ruan, Wenjie Chen +2 | — | 11 Sept 2026 | — | — | — | — |
| From Monolithic Blending to Agentic Orchestration: Dynamic Response for Conversational Assistants at ScalearXiv:2609.05758cs.AI | Cen Mia Zhao, Peng Wang, Chuan Shi +2 | — | 11 Sept 2026 | — | — | — | — |