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 |
|---|---|---|---|---|---|
| TimeSage-EV: A Live Benchmark for Agentic Time Series Analysis in Evolving Environments Anna Vettoruzzo, Joaquin Vanschoren, Ming Jin, Qingren Yao Published: 2026-08-14Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-14 | cs.AI | ai-safety, csai, preprint | E10 / R9 (88%) | - |
| Towards Efficient Multimodal and Multilingual Opinion Extraction for STI: A QLoRA-Based Fine-Tuning Approach Jiacheng Wang, Sheng Hong, Xuanqi Wang, Yuwei Wang Published: 2026-08-14Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-14 | cs.AI | ai-safety, csai, preprint | E8 / R6 (94%) | - |
| Traj-LeWM: Path-Aware World-Model Planning via Latent Trajectory Cost Jiayu Chen, Jingtian Wan, Tao Huang, Xiaodi Huang Published: 2026-08-14Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-08-14 | cs.AI | ai-safety, csai, preprint | E11 / R10 (93%) | 15 |
| Tripwire: Triggering Aligned Refusal via Statistically Certified Safety Neurons Jun Sun, Peixin Zhang, Wei Zhao, Zhe Li Published: 2026-08-14Area: cs.AICitations: 35 Tags: ai-safety, csai, preprint | 2026-08-14 | cs.AI | ai-safety, csai, preprint | E13 / R10 (90%) | 35 |
| Trust Is Not Enough: Influence Calibration for On-Policy Self-Distillation in Agentic RL Jung Im Choi, Lijing Zhu, Mengchen Fan, Moule Lin Published: 2026-08-14Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-14 | cs.AI | ai-safety, csai, preprint | E11 / R10 (91%) | - |
| Twin: Playing an Unknown Game with a Test-Time Digital Twin Alexy Skoutnev, Gaston Longhitano, Iddo Drori, Kevin Ellis Published: 2026-08-14Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-14 | cs.AI | ai-safety, csai, preprint | - | - |
| What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering Carl Yang, Guanchen Wu, Jiayuan Ding, Subhabrata Mukherjee Published: 2026-08-14Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-14 | cs.AI | ai-safety, csai, preprint | E12 / R9 (91%) | - |
| When Is an Agent Evaluation Over? Outcome Finality and Cross-Unit Separation Avyay M. Casheekar Published: 2026-08-14Area: cs.AICitations: - Tags: ai-safety, csai, preprint, safety-evaluation | 2026-08-14 | cs.AI | ai-safety, csai, preprint, safety-evaluation | E9 / R6 (92%) | - |
| When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict Longbo Huang, Lu Yang, Shusheng Xu, Tongkai Yang Published: 2026-08-14Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-14 | cs.AI | ai-safety, csai, preprint | E9 / R8 (91%) | - |
| Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages Anjir Ahmed Chowdhury, Cheng-Hau Yang, Chih-Hsuan Yang, Eliu A. Huerta Published: 2026-08-14Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-14 | cs.AI | ai-safety, csai, preprint | E8 / R6 (94%) | - |
| Wyvern: An Agentic Framework for Generating Grounded Multimodal Reports Alessio Burrello, Beatrice Alessandra Motetti, Daniele Jahier Pagliari, Emilien Guandalino Published: 2026-08-14Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-14 | cs.AI | ai-safety, csai, preprint | - | - |
| Academic League of Artificial Intelligence - An Integrative Perspective of Teaching, Research, and Extension Agenor Hentz, Alexandre Leopoldo Gon莽alves, Alison R. Panisson, Andr茅a Sabedra Bordin Published: 2026-08-13Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-13 | cs.AI | ai-safety, csai, preprint | E7 / R6 (94%) | - |
| Academic League of Artificial Intelligence - An Integrative Perspective of Teaching, Research, and Extension Agenor Hentz, Alexandre Leopoldo Gon莽alves, Alison R. Panisson, Andr茅a Sabedra Bordin Published: 2026-08-13Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-13 | cs.AI | ai-safety, csai, preprint | E9 / R6 (92%) | - |
| A Calibrated Test of Internal Action Maps: State Signals Without Global Affine Closure Dekun Yang Published: 2026-08-13Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-13 | cs.AI | ai-safety, csai, preprint | E10 / R7 (96%) | - |
| Agent Behavioral Contracts II: Certifying Compositional Reliability Without Assuming Independence Arun Pratap Bhardwaj, Garima Singh, Varun Pratap Bhardwaj Published: 2026-08-13Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-08-13 | cs.AI | ai-safety, csai, preprint | E7 / R5 (89%) | 15 |
| AI and Consumer Rights in India Working Paper Balaraman Ravindran, Omir Kumar, Sriya Sridhar, Vibhav Mithal Published: 2026-08-13Area: cs.AICitations: 16 Tags: ai-safety, csai, preprint | 2026-08-13 | cs.AI | ai-safety, csai, preprint | E10 / R6 (90%) | 16 |
| AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1) AlayaWorld Team, Chuanhao Li, Jiaming Tan, Kaipeng Zhang Published: 2026-08-13Area: cs.AICitations: 3 Tags: ai-safety, csai, preprint | 2026-08-13 | cs.AI | ai-safety, csai, preprint | E10 / R7 (91%) | 3 |
| ARAC: Benchmarking Auto-Research's Alignment and Completeness on End-to-End Researchs Jiafei Wu, Jiale Cui, Kaixi Zhong, Xiaogang Xu Published: 2026-08-13Area: cs.AICitations: 36 Tags: ai-safety, alignment-training, csai, preprint | 2026-08-13 | cs.AI | ai-safety, alignment-training, csai, preprint | E14 / R13 (90%) | 36 |
| ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction Choy Zhen Wen Marcus, Jiang-Ming Yang, Jianshe Li, Kewei Fu Published: 2026-08-13Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-13 | cs.AI | ai-safety, csai, preprint | E11 / R11 (91%) | - |
| A Unifying Perspective on Causal World Models: From Observations to Representations to Structure Avinash Kori, Fabrizio Russo Published: 2026-08-13Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-13 | cs.AI | ai-safety, csai, preprint | E8 / R6 (92%) | - |
| Behavioral Reprogramming of Open-Weights Models: Cognitive Plasticity and Alignment Bounds Lucia Mal铆膷kov谩 Published: 2026-08-13Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-08-13 | cs.AI | ai-safety, alignment-training, csai, preprint | E8 / R5 (93%) | - |
| Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development Borun Chen, Fei Sun, Hao Tian, Hexiang Tan Published: 2026-08-13Area: cs.AICitations: - Tags: ai-safety, csai, preprint, safety-evaluation | 2026-08-13 | cs.AI | ai-safety, csai, preprint, safety-evaluation | E12 / R12 (91%) | - |
| Beyond Retrieval: Query-Conditioned Reuse of Long-Horizon Agent Trajectories Hang Yan, Heng Wang, Jiashuai Liu, Lingling Zhang Published: 2026-08-13Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-13 | cs.AI | ai-safety, csai, preprint | E8 / R7 (94%) | - |
| Beyond the Best Guess: Improving LLM Solution Coverage with Evolution Strategies Babak Hodjat, Conor F. Hayes, Elliot Meyerson, Kajetan Schweighofer Published: 2026-08-13Area: cs.AICitations: 45 Tags: ai-safety, csai, preprint | 2026-08-13 | cs.AI | ai-safety, csai, preprint | E10 / R7 (93%) | 45 |
| BoardroomAI: Dependency-Aware Human-Steerable Multi-Agent Deliberation through Evolving Decision Graphs Sanjeev Manivannan Published: 2026-08-13Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-13 | cs.AI | ai-safety, csai, preprint | E6 / R6 (91%) | - |
| CABS+: Efficient and Scalable Model Merging via Conflict-Aware Sparsification and Adaptive Weight Allocation Binhang Qi, Hailong Sun, Xiang Gao, Yuchen Liu Published: 2026-08-13Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-13 | cs.AI | ai-safety, csai, preprint | E9 / R8 (92%) | - |
| Capability Sheaves for Compositional Agent-Harness Repair: Controlled Quotients and a Real-Repository Stress Test Saveliy Batruin Published: 2026-08-13Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-13 | cs.AI | ai-safety, csai, preprint | E7 / R5 (89%) | - |
| Correct Is Not Governed: Provenance Integrity in Agentic Workflows Jesus Salas Published: 2026-08-13Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-13 | cs.AI | ai-safety, csai, preprint | E10 / R7 (91%) | - |
| Coverage Aware Active Evaluation for Failure Discovery with Paired Systems Anjali Parashar, Apoorva Sharma, Carson Sobolewski, Chuchu Fan Published: 2026-08-13Area: cs.AICitations: - Tags: ai-safety, csai, preprint, safety-evaluation | 2026-08-13 | cs.AI | ai-safety, csai, preprint, safety-evaluation | E8 / R8 (91%) | - |
| Decomposition of Evidence, Contradiction, and Fragility in Perturbation Responses Lei You Published: 2026-08-13Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-13 | cs.AI | ai-safety, csai, preprint | E8 / R8 (90%) | - |