Instant research discovery
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
PreviousNext
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Beyond Outcome Feedback: Trajectory-Quality-Guided Experience-based Learning Benshuo Fu, Bingjie Zhang, Dandan Guo, Qiantong Liu Published: 2026-10-10Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-10 | cs.AI | ai-safety, csai, preprint | - | - |
| Bridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling Heming Zou, Jiarong Wen, Kaiyu Zhang, Lizhou Cai Published: 2026-10-10Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-10 | cs.AI | ai-safety, csai, preprint | - | - |
| Can agents whose sole duty is to keep humans alive be hijacked to kill? Delayed multi-turn derived-action trap attacks in simulated high-stakes environments Josef A. Habdank Published: 2026-10-10Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-10 | cs.AI | ai-safety, csai, preprint | - | - |
| Can You Trust Your Preference Models? Stackelberg Games for Alignment Aditya Agrawal, Riccardo Formenti, Vikas Garg Published: 2026-10-10Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-10-10 | cs.AI | ai-safety, alignment-training, csai, preprint | - | - |
| CB-Agent: Concept-Based In-Context Learning for Sequential Action Selection Huaze Tang, Minyu Zhang, Qingyue Zhang, Shao-Lun Huang Published: 2026-10-10Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-10 | cs.AI | ai-safety, csai, preprint | E11 / R10 (95%) | - |
| Certify the Decision, Not Every Score: Exact Top-k Selection from Few Evaluations Yingzhi Tang, Yuhe Sui Published: 2026-10-10Area: cs.AICitations: - Tags: ai-safety, csai, preprint, safety-evaluation | 2026-10-10 | cs.AI | ai-safety, csai, preprint, safety-evaluation | - | - |
| CESNET-TimeSeries26: A Multi-Year Network Traffic Time Series Dataset for Annual Seasonality, Concept Drift, and Long-Term Anomaly Detection Josef Koumar, Kamil Jerabek, Karel Hynek, Pavel Siska Published: 2026-10-10Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-10 | cs.AI | ai-safety, csai, preprint | - | - |
| Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval Bing He, Franck Dernoncourt, Haoyu Han, Huiyuan Chen Published: 2026-10-10Area: cs.IRCitations: - Tags: ai-safety, csir, preprint | 2026-10-10 | cs.IR | ai-safety, csir, preprint | E8 / R7 (90%) | - |
| Coarse-Graining Recursive Expert Computation: Continuation-Relative Interfaces and Failure Modes Shihua Yu, Tianchi Chen, Yanzhi Wang Published: 2026-10-10Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-10 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (91%) | - |
| Compositional Concepts Erasing: Disentangling Object-Style via Domain Manifold Unlearning Bo Hui, Gen Li, Kaiyuan Deng, Xiaolong Ma Published: 2026-10-10Area: cs.CVCitations: - Tags: ai-safety, cscv, preprint | 2026-10-10 | cs.CV | ai-safety, cscv, preprint | E15 / R12 (90%) | - |
| Conflict-Aware Autonomous Resource Orchestration for 5G Edge Slicing Using Multi-Agent Systems and LLMs Fl谩vio de Oliveira Silva, Juliano Araujo Wickboldt, Nathan R. Prediger, Paulo Novais Published: 2026-10-10Area: cs.NICitations: - Tags: ai-safety, csni, preprint | 2026-10-10 | cs.NI | ai-safety, csni, preprint | E13 / R9 (94%) | - |
| Continuous Risk-Based Scheduling for Food Safety Inspection: Integrating Historical Decay with Event-Driven Consumer Review Signals Akriti Bhat, Ishan Gupta, Wayne Zhu Published: 2026-10-10Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-10 | cs.AI | ai-safety, csai, preprint | - | - |
| Counterfactual Regret for Reflective Agents with Lean-Verified Guarantees Mengting Xu, Peng Ying, Shi Xu, Xinzheng Xu Published: 2026-10-10Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-10 | cs.AI | ai-safety, csai, preprint | - | - |
| Counterfactual Rollouts for Offline Contrastive Goal-Conditioned Reinforcement Learning Ai Bo, Junzhe Zhang, Tingrui Huang Published: 2026-10-10Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-10 | cs.LG | ai-safety, cslg, preprint | - | - |
| Cross-Lingual TTS for Indian Languages: A Benchmark and Inference-Time Duration Estimation Strategies Adarsh Arigala, Arjun Gangwar, Srinivasan Umesh Published: 2026-10-10Area: eess.ASCitations: - Tags: ai-safety, eessas, preprint | 2026-10-10 | eess.AS | ai-safety, eessas, preprint | - | - |
| CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation Chenlu Ding, Jiancan Wu, Tianyu Zhang, Xiangnan He Published: 2026-10-10Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-10 | cs.AI | ai-safety, csai, preprint | - | - |
| Decoupling Knowledge Forgetting and Refusal Learning in MLLM Unlearning Dong Liang, Haodong Chen, Lingbing Guo, Shengtao Wen Published: 2026-10-10Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-10 | cs.AI | ai-safety, csai, preprint | E9 / R6 (91%) | - |
| Deep Learning-based Semantic Segmentation of Dental Radiographs: Comparative Evaluation of PSPNet, DeepLabv3, UNet, and UNet++ Malithi Nawarathne, Nadeesha Herath Mudiyanselage Lihini Sangeetha Published: 2026-10-10Area: cs.CVCitations: - Tags: ai-safety, cscv, preprint, safety-evaluation | 2026-10-10 | cs.CV | ai-safety, cscv, preprint, safety-evaluation | - | - |
| Depth-progressive 3D seismic velocity model building via 2D generative diffusion models Mohammad H. Taufik, Randy Harsuko, Shijun Cheng, Tariq Alkhalifah Published: 2026-10-10Area: physics.geo-phCitations: - Tags: ai-safety, physicsgeo-ph, preprint | 2026-10-10 | physics.geo-ph | ai-safety, physicsgeo-ph, preprint | - | - |
| DexCast: Learning Real-World Dexterous Control from Human Videos Haoqian Wang, Kaisheng Liu, Mengzhe Wang, Runqing Cheng Published: 2026-10-10Area: cs.ROCitations: - Tags: ai-safety, csro, preprint | 2026-10-10 | cs.RO | ai-safety, csro, preprint | E12 / R11 (92%) | - |
| Diffusion-Based Auctions for Multi-Winner Banner Ads Constantinos Daskalakis, Fucheng Warren Zhu, Giannis Daras, Henry Huang Published: 2026-10-10Area: cs.GTCitations: 12 Tags: ai-safety, csgt, preprint | 2026-10-10 | cs.GT | ai-safety, csgt, preprint | E9 / R8 (95%) | 12 |
| Does Failure Feedback Direct Agent Self-Modification? Rong He Published: 2026-10-10Area: cs.SECitations: 27 Tags: ai-safety, csse, preprint | 2026-10-10 | cs.SE | ai-safety, csse, preprint | E8 / R6 (92%) | 27 |
| DSABench: Benchmarking Source Discovery, Coordination, and Execution for Multi-Database Agents Bo Xu, Haoran Wu, Jinlong Luo Published: 2026-10-10Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-10 | cs.AI | ai-safety, csai, preprint | - | - |
| EAIR: Interaction Risks in Enterprise LLM Multi-Agent Systems Jianfeng Gao, Michel Galley, Paulo Salem, Robert Sim Published: 2026-10-10Area: cs.MACitations: - Tags: ai-safety, csma, preprint | 2026-10-10 | cs.MA | ai-safety, csma, preprint | E13 / R10 (95%) | - |
| EarthAlign: Learning Language-Aligned Representations of Earth System Data Dat Tien Nguyen, Duncan Watson-Parris, Fadillah Adamsyah Maani, Jiaqi Ma Published: 2026-10-10Area: cs.CVCitations: 12 Tags: ai-safety, cscv, preprint | 2026-10-10 | cs.CV | ai-safety, cscv, preprint | E11 / R10 (93%) | 12 |
| Energy Ring: Stabilizing Feature Energy for Reliable Test-Time Discovery Chenggong Ni, Fan Lyu, Fuyuan Hu, Rui Yao Published: 2026-10-10Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-10 | cs.AI | ai-safety, csai, preprint | E6 / R4 (91%) | 15 |
| Equal-information evaluation of credit assignment in modular financial reinforcement learning Gennadiy Chistiakov, Yury Yanovich Published: 2026-10-10Area: cs.AICitations: - Tags: ai-safety, csai, preprint, safety-evaluation | 2026-10-10 | cs.AI | ai-safety, csai, preprint, safety-evaluation | - | - |
| EvoCowork: A Benchmark for Real-World Office Tasks Kaixiong Ting, Ningxin Pan, Wentao Zhang, Xingyan Chen Published: 2026-10-10Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-10 | cs.AI | ai-safety, csai, preprint | - | - |
| Exploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models Lass Najmuldeen, Seyedhamidreza Mousavi Published: 2026-10-10Area: cs.LGCitations: - Tags: adversarial-robustness, ai-safety, cslg, preprint | 2026-10-10 | cs.LG | adversarial-robustness, ai-safety, cslg, preprint | - | - |
| Exposing AI Inference as a Telco Network API over the 5G User Plane Fl谩vio de Oliveira Silva, Joberto S. B. Martins, Larissa Ferreira Rodrigues Moreira, Rodrigo Moreira Published: 2026-10-10Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-10 | cs.AI | ai-safety, csai, preprint | - | - |