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 Probabilistic Logic Programs with Functional Gradient Guided Language Models Bhavan Vasu, Farbod Tavakkoli, Kristian Kersting, Prasad Tadepalli Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E10 / R9 (90%) | - |
| Learning to Plan by Looking Back: Hindsight Hierarchies for Training Reasoning Models Holger Eble, Lars Simon, Manuel Radons Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E7 / R6 (94%) | - |
| LEVER: Adaptive Cost-Aware Proof Search Over AND/OR Graphs Begum Cicekdag, Nihal Jain, Shuangjie Yao, Suman Jana Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E10 / R10 (93%) | - |
| LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models Surya Shetty, Ulisses Braga-Neto Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E12 / R10 (90%) | - |
| Looking Inside LLMs: Small-World Connectivity as a Signature of Reasoning Performance Dawei Zhou, Elynn Chen, Enpei Zhang, Rex Ying Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E10 / R7 (91%) | - |
| MagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data Synthesis Aviral Kumar, David Acuna, Jan Kautz, Ximing Lu Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E10 / R8 (89%) | - |
| MedBenchAgent: Towards Systematic Automation of Medical VLM Benchmark Construction Guangjing Yang, Jiabao Zhou, Jin Yin, Junren Wang Published: 2026-10-08Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E22 / R16 (83%) | 15 |
| Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks Haitham Bou-Ammar, Haoyu Zhao, Jun Wang, Meng Fang Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E7 / R6 (92%) | - |
| Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies Derong Xu, Junyi Li, Maolin Wang, Pengyue Jia Published: 2026-10-08Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E14 / R9 (92%) | 15 |
| MemTrial: Learning When to Trust Memory in LLM Portfolio Agents Guanghao Wu, Shoujin Wang, Zhuo Cai Published: 2026-10-08Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E9 / R7 (92%) | 15 |
| MetaOPD: Meta-Learned Token Weighting for On-Policy Distillation Fei Wu, Kun Kuang, Min Zhang, Pingchen Lu Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E7 / R6 (92%) | - |
| MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation Chenglin Wu, Cheng Yang, Fanqi Kong, Hong Chang Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E6 / R5 (91%) | - |
| Mine Odyssey: Benchmarking Spatial Agentic Intelligence in the Wild Hao Li, Junlong Li, Junxian He, Yuxuan Cao Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E10 / R8 (95%) | - |
| MultiWorldBench: Do Independently Controlled Views Describe One Shared World? Rui Hu, Ruoxi Zhang, Xitong Li, Yisong Wang Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E10 / R12 (92%) | - |
| MultiWorldBench: Do Independently Controlled Views Describe One Shared World? Rui Hu, Ruoxi Zhang, Yisong Wang, Zhangbo Xu Published: 2026-10-08Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E10 / R10 (94%) | 15 |
| OA-MAP: Evidence-Grounded Multi-Agent Multimodal Framework for Interpretable Knee Osteoarthritis Progression Mingrui Yang, Qiang Guan, Sixu Chen, Xiaojuan Li Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E10 / R11 (93%) | - |
| Onboard Marine Anomaly Detection on $桅$sat-2: From Simulation-Based Development to In-Orbit Demonstration Adrien Girard, Benjamin Francesconi, Clotilde Szywala, Marjorie Bellizzi Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E12 / R11 (94%) | - |
| One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails Erfan Baghaei Potraghloo, Massoud Pedram, Seyedarmin Azizi Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E11 / R8 (96%) | - |
| On the estimation and validity of AI time horizons---a statistical look at the METR plot Drew T. Nguyen, William Fithian Published: 2026-10-08Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E10 / R6 (93%) | 15 |
| OnTrack: Real-Time Monitoring and Intervention in LLM Agent Trajectories via Streaming Structure-Aware Optimal Transport Babak Barazandeh, Chinmay Kulkarni, Connor Swanson, Nikhil Mungel Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E6 / R5 (91%) | - |
| Open-ended Scientific Discovery with Possibilistic Reasoning Anita Yang, Krikamol Muandet, Masaki Adachi, Siu Lun Chau Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E6 / R5 (94%) | - |
| OpenProblemBench: Benchmarking AI on Open Problems in the Foundational Theoretical Sciences Kun Chen, Sihan Hu, Tianning Xiao, Xiansheng Cai Published: 2026-10-08Area: cs.AICitations: 1 Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E16 / R9 (95%) | 1 |
| ORDO: Operation-level Round-aware Dynamic Ordering for MIP Presolve Chunhe Song, Zehuan Chen Published: 2026-10-08Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E10 / R6 (92%) | 15 |
| Overcoming Prior Barriers: Supervised Fine-Tuning under Long-Tail Distribution Chris North, Dawei Zhou, Dongqi Fu, Haohui Wang Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E6 / R5 (93%) | - |
| Prior or Feedback? What an LLM Uses When Adapting Neural Operators Javier Mora Jimenez, Julian Chan Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E8 / R8 (91%) | - |
| Probability-Signature Dynamics: Unpacking Modular Addition Learning Within Two-Layer Networks Junjie Yao, Linyu Liu, Pinyan Lu, Yunji Wang Published: 2026-10-08Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E8 / R6 (92%) | 15 |
| PulseBound: Future-Beat State Forecasting Under an Explicit Information Boundary Chenyang Xu, Dezhen Wang, Donglin Xie, Guangpu Zhu Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E8 / R7 (92%) | - |
| Q-Shaped Options for Hierarchical Reinforcement Learning Alexey Zakharov, Antoine Gorceix, Antonio L茅on Villares, Clarisse Wibault Published: 2026-10-08Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E10 / R8 (91%) | 15 |
| RaReCache: Bridging the Gap in Cross-Model KV Cache Reuse via Rank disagreement-based Selective Recomputation Peter A. Beerel, Saptarshi Mitra, Sitao Huang, Souvik Kundu Published: 2026-10-08Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E10 / R8 (92%) | - |
| ReCast: Attribution-Oriented Step Representation Learning for LLM-Based Agent Systems Haoyang Huang, Mingyu Wang, Nan Duan, Taiyu Zhu Published: 2026-10-08Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-08 | cs.AI | ai-safety, csai, preprint | E14 / R12 (93%) | 15 |