| TRACE: Training Reasoning Agents for Causal Exploration with Synthesized RewardsarXiv:2609.10315cs.AI | Rui Sun, Zhan Shi, Bing He | — | 11 Sept 2026 | — | — | — | — |
| From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric ReasoningarXiv:2609.10335cs.AI | Weichen Dai, Rafael Medeiros Cabral, Ziyi Shou +2 | — | 11 Sept 2026 | — | — | — | — |
| Cyber-Financial Contagion: Modeling the Propagation of an AI Vendor Compromise Through the Banking SystemarXiv:2609.10350cs.AI | Alex Leytes | — | 11 Sept 2026 | — | — | — | — |
| Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMsarXiv:2609.10413cs.AI | Ansuman Mullick, Eray T\"uz\"un | — | 11 Sept 2026 | — | — | — | — |
| ConvMem: Convolutional Memory for Long-Context ReasoningarXiv:2609.10441cs.AI | Hongming Zhang, Zhaozhen Gu, Fengshuo Bai +2 | — | 11 Sept 2026 | — | — | — | — |
| JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task CompositionarXiv:2609.10451cs.AI | Zixiang Chen, Yuheng Lu, Zihao Cheng +2 | — | 11 Sept 2026 | — | — | — | — |
| Quantifying Logical Consistency in Transformers via Query-Key AlignmentarXiv:2502.17017cs.CL | Eduard Tulchinskii, Anastasia Voznyuk, Laida Kushnareva +2 | — | 11 Sept 2026 | — | — | — | — |
| From Plausible to Actionable: A Position on LLM Self-ExplanationsarXiv:2607.15957cs.CL | Elize Herrewijnen, Benedetta Muscato, Gizem Gezici +1 | — | 11 Sept 2026 | — | — | — | — |
| Characterizing Text Branch Sensitivity in Medical Vision-Language Segmentation via Evidence DecouplingarXiv:2609.02663cs.CV | Ziquan Liu, Zhewei Zhu, Xuyang Shi | — | 11 Sept 2026 | — | — | — | — |
| Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language ModelsarXiv:2609.03247cs.CR | Syed Ghazanfar Abbas, Dongyan Xu | — | 11 Sept 2026 | — | — | — | — |
| AgenticGen: Reward-Guided Agentic Video Generation for AdvertisingarXiv:2609.09187cs.CV | Xingyuan Bu, Chengru Song, Hao Zhou +2 | — | 11 Sept 2026 | — | — | — | — |
| Reliability-Aware Hybrid-K Ensemble Selection for Cervical Cytology Classification: Integrating Discrimination, Calibration, and Selective PredictionarXiv:2609.09189eess.IV | Nisreen Albzour, Sarah S. Lam | — | 11 Sept 2026 | — | — | — | — |
| AgentHijack: Visual Patch Attacks on Multimodal Computer-Use AgentsarXiv:2609.09212cs.CR | Zhihao Liu, Hongyu Sun, Zhiyuan Fu +2 | — | 11 Sept 2026 | — | — | — | — |
| Geometry Conditioning in an Embodied SLM: Training Controls and Robustness Diagnostics in a 0.8B Hybrid ModelarXiv:2609.09213cs.RO | Hao Li, Haofei Sun, Lin He | — | 11 Sept 2026 | — | — | — | — |
| Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research AgentsarXiv:2609.09219cs.MA | Jingjie Ning, Shanshan Zhong, Xiaochuan Li +1 | — | 11 Sept 2026 | — | — | — | — |
| Compute-Bounded Security Assurance - Coverage, Verification, and Response under Resource ConstraintsarXiv:2609.09229cs.CR | Jithin VG, Ditto PS | — | 11 Sept 2026 | — | — | — | — |
| Scaling Post-Training Ternarisation to Qwen3-8B Capability Retention, Reproduction, Lossless Packing, and Packed ExecutionarXiv:2609.09240cs.LG | Anirudh Malik, M Sparsh Mehra, Poojith Devan | — | 11 Sept 2026 | — | — | — | — |
| Distribution-Consistent Inference for Dynamic Sparse Mixture-of-ExpertsarXiv:2609.09241cs.LG | Dohyeon Kim, Bedionita Soro, Sung Ju Hwang | — | 11 Sept 2026 | — | — | — | — |
| Talking to Itself While Coding: What Makes Comments Help Code Generation?arXiv:2609.09242cs.SE | Dangfeng Pan, Zhensu Sun, Cenyuan Zhang +2 | — | 11 Sept 2026 | — | — | — | — |
| In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document PoisoningarXiv:2609.09243cs.CR | Iliano Fasolino | — | 11 Sept 2026 | — | — | — | — |
| Critical initialization destabilizes higher input derivatives in wide scalar-input networksarXiv:2609.09244stat.ML | Prashant Singh, Pranav Singh | — | 11 Sept 2026 | — | — | — | — |
| What Fixed-Rollout pass@k Evaluations Can IdentifyarXiv:2609.09245stat.ML | Pranav Singh, Prashant Singh | — | 11 Sept 2026 | — | — | — | — |
| No Free Checker: A Survey of Verifiers for Robot PoliciesarXiv:2609.09250cs.RO | Yang Wan, Xihang Yue, Zhirui Liu +2 | — | 11 Sept 2026 | — | — | — | — |
| DiffLUT-Net: Differentiable Training of FPGA LUT Networks with Learnable ConnectivityarXiv:2609.09254cs.LG | Jiaqi Ye, Xinrui Gong, Jingcun Wang +2 | — | 11 Sept 2026 | — | — | — | — |
| Voice or Stereotype? Disentangling Acoustic and Content-Based Gender in Speech-to-Speech ModelsarXiv:2609.09263cs.SD | Xiaoqun Liu, Tanu Mitra, Harshit Rajgarhia +1 | — | 11 Sept 2026 | — | — | — | — |