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 |
|---|---|---|---|---|---|
| Learning Hierarchical Skill Policies with Offline Quality-Diversity Reinforcement Learning Takayuki Osa, Tanachai Anakewat, Tatsuya Harada Published: 2026-08-20Area: cs.AICitations: 23 Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E10 / R7 (89%) | 23 |
| Learning When to Think: Adaptive Reasoning for Test-Time Compute Allocation Gijs Kassenaar, Vincent François-Lavet, Zhao Yang Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E10 / R9 (95%) | - |
| Learning When to Think: Adaptive Reasoning for Test-Time Compute Allocation Gijs Kassenaar, Vincent François-Lavet, Zhao Yang Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E8 / R8 (96%) | - |
| LLMs as Acquisition Policies for Finite-Pool Materials Optimization: A Controlled Study Dino-Rober Demir, Florian Le Bronnec, Rio Yokota Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E14 / R6 (88%) | - |
| Lost in Translation: How Universal Ethical Values Fail to Translate Across Global Contexts Cesar Cervera, Daricia Wilkinson, Jenny Yang, Karla Badillo-Urquiola Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E12 / R11 (90%) | - |
| Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking Pengfei Wan, Shengyi Liao, Tao Lin, Yansen Han Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E9 / R6 (93%) | - |
| MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use Haoming Xu, Haozhe Luo, Jizhan Fang, Junfeng Fang Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E15 / R15 (95%) | - |
| MidTool: Mid-training Data Synthesis for Agentic Tool Use Boyi Liu, Canwen Xu, Fengqing Jiang, Radha Poovendran Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E14 / R11 (90%) | - |
| On the Applicability of Safety Nets: A Safety-By-Design Solution for Certifying Neural Networks Elena Hoemann, Frank Köster, Johann Maximilian Christensen, Sven Hallerbach Published: 2026-08-20Area: cs.AICitations: 53 Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E13 / R11 (92%) | 53 |
| Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their Own Computation Emilio Ferrara Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E8 / R7 (92%) | - |
| Optimal Skill Selection for LLM Agents with Provable Bicriteria Guarantees Longbo Huang, Ruishuo Chen, Xun Wang, Yu Chen Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E6 / R5 (92%) | - |
| Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation Adam Fisch, Fantine Huot, Jacob Eisenstein, Kate Larson Published: 2026-08-20Area: cs.AICitations: 50 Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E9 / R5 (94%) | 50 |
| Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation Adam Fisch, Fantine Huot, Jacob Eisenstein, Kate Larson Published: 2026-08-20Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E11 / R8 (92%) | 15 |
| Phantom Gains: Auditing Self-Improvement Against a Measured Null Cheng Xu, Liming Chen, M-Tahar Kechadi, Nan Yan Published: 2026-08-20Area: cs.AICitations: 45 Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E13 / R9 (94%) | 45 |
| PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents Seongjae Kang, Sung Ju Hwang, Taehyung Yu Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E10 / R8 (92%) | - |
| QUASAR: A Quantum-Classical Neural Network for SAR Satellite Physical-Layer Authentication Nathanael Denis, Roberto Di Pietro, Vincenzo Sammartino Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E10 / R9 (91%) | - |
| ReguSim: Evaluating LLM Agent Rule Grounding in Financial Compliance Anyi Rao, Liang Lan, Lin Willian Cong, Qijun Xie Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E10 / R10 (92%) | - |
| Rethinking Patch Based Multivariate Time Series Forecasting with Semantic Structured Partitioning Jiazhe Wang, Linjing Xue, Meiwen Li, Ming Liu Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E10 / R8 (91%) | - |
| Rethinking the Evaluation and Optimization of LLM-Based Social Simulation Ji-Rong Wen, Pei Wang, Xu Chen Published: 2026-08-20Area: cs.AICitations: 33 Tags: ai-safety, csai, preprint, safety-evaluation | 2026-08-20 | cs.AI | ai-safety, csai, preprint, safety-evaluation | E8 / R6 (94%) | 33 |
| Rule-Compliant Visual Spatial Planning for Multimodal Large Language Models Jia Cai, Ting Lei, Yang Liu, Yaoyi Li Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E8 / R6 (94%) | - |
| SafeBranch: Branch-Pair Safety Alignment for Embodied Agents Haneul Lee, Hyunse Lee, Jiwoo Jeong, Kyochul Jang Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-08-20 | cs.AI | ai-safety, alignment-training, csai, preprint | E12 / R12 (90%) | - |
| SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning Bo An, Dayang Liang, Lang Feng, Yunlong Liu Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E8 / R7 (93%) | - |
| Scientific Data Skills: Enabling Agent-Ready Scientific Data Services at Scale Chenyang Zhao, Haotian Chen, Hao Wang, Hengshu Zhu Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E6 / R6 (93%) | - |
| Specification-delta-driven data governance: an empirical study of the «spec-delta» as the unit of change in lakehouse data platforms Pablo Ramirez Amador Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E15 / R10 (93%) | - |
| Spike-based Belief Propagation in Nonlinear Dynamical Systems Bert de Vries, Hongye Wang, Sepideh Adamiat, Wouter M. Kouw Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E10 / R10 (94%) | - |
| STCO: Conditional Neural Operators for Time-Dependent PDEs Juan Li, Xingxin Yang, Zhan Zhang Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E7 / R9 (92%) | - |
| Symposium: Trust via Auditable Records for Communities of AI Scientist Agents Dexter Pratt Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E9 / R6 (93%) | - |
| Terminal Agents: A Survey of AI Agents in Command-Line Environments Chen Qian, Haoxi Zeng, Heng Tao Shen, Jingkuan Song Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E7 / R11 (89%) | - |
| TESTNAV: Pareto-Guided Search for Compositional Robustness Testing Alexandros Koliousis, Arooj Arif, Elena Botoeva, Tobias Hartung Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E16 / R15 (94%) | - |
| The Third Restructuring of Software Form: From the Three-Tier Architecture to Storage, Models, and Agents Changgui Hong, Tao Zhou, Wei Lin, Zhaofei Xie Published: 2026-08-20Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-20 | cs.AI | ai-safety, csai, preprint | E10 / R14 (91%) | - |