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 |
|---|---|---|---|---|---|
| AdaRubric: Task-Adaptive Rubrics for LLM Agent Evaluation Liang Ding Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint, safety-evaluation | 2026-03-22 | cs.AI | ai-safety, csai, preprint, safety-evaluation | E7 / R3 (98%) | - |
| AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling Liang Ding Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E7 / R3 (97%) | - |
| ARYA: A Physics-Constrained Composable & Deterministic World Model Architecture Lukasz Chmiel, Seth Dobrin Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E5 / R3 (95%) | - |
| A transformer architecture alteration to incentivise externalised reasoning Cameron Tice, Edward James Young, Elizabeth Pavlova, Karthik Viswanathan Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E5 / R3 (95%) | - |
| A transformer architecture alteration to incentivise externalised reasoning Cameron Tice, Edward James Young, Elizabeth Pavlova, Karthik Viswanathan Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E6 / R4 (94%) | - |
| AutoMOOSE: An Agentic AI for Autonomous Phase-Field Simulation Henry Chan, Subramanian K. R. S. Sankaranarayanan, Sukriti Manna Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E5 / R3 (98%) | - |
| Behavioural feasible set: Value alignment constraints on AI decision support Taejin Park Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-22 | cs.AI | ai-safety, alignment-training, csai, preprint | E5 / R3 (94%) | - |
| Can LLMs Fool Graph Learning? Exploring Universal Adversarial Attacks on Text-Attributed Graphs Dalin Zhang, Kai Wu, Pengfei Jiao, Xiang Ao Published: 2026-03-22Area: cs.AICitations: - Tags: adversarial-robustness, ai-safety, csai, preprint | 2026-03-22 | cs.AI | adversarial-robustness, ai-safety, csai, preprint | E5 / R3 (97%) | - |
| Can we automatize scientific discovery in the cognitive sciences? Akshay K. Jagadish, Eric Schulz, Kristin Witte, Marcel Binz Published: 2026-03-22Area: cs.AICitations: 21 Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E5 / R3 (95%) | 21 |
| ConsRoute:Consistency-Aware Adaptive Query Routing for Cloud-Edge-Device Large Language Models Haoyu Qiao, Hao Zhang, Jie Liu, Shanwen Mao Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E4 / R3 (95%) | - |
| Does AI Homogenize Student Thinking? A Multi-Dimensional Analysis of Structural Convergence in AI-Augmented Essays Go Maeda, Keito Inoshita, Kentaro Tsuji, Michiaki Omura Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E5 / R3 (95%) | - |
| DomAgent: Leveraging Knowledge Graphs and Case-Based Reasoning for Domain-Specific Code Generation Dhasarathy Parthasarathy, Robert Feldt, Shuai Wang, Yinan Yu Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E5 / R3 (96%) | - |
| DomAgent: Leveraging Knowledge Graphs and Case-Based Reasoning for Domain-Specific Code Generation Dhasarathy Parthasarathy, Robert Feldt, Shuai Wang, Yinan Yu Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E5 / R3 (95%) | - |
| Dynamic Fusion-Aware Graph Convolutional Neural Network for Multimodal Emotion Recognition in Conversations Jun Zhou, Keqin Li, Tao Meng, Wei Ai Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E6 / R4 (97%) | - |
| Graph of States: Solving Abductive Tasks with Large Language Models Dan Pei, Jiamin Jiang, Jiasong Feng, Lu Teng Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E5 / R3 (96%) | - |
| Improving Coherence and Persistence in Agentic AI for System Optimization Hari Balakrishnan, Kimia Noorbakhsh, Mohammad Alizadeh, Pantea Karimi Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E5 / R3 (95%) | - |
| Intelligence Inertia: Physical Principles and Applications Jipeng Han Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E5 / R3 (94%) | - |
| Is the future of AI green? What can innovation diffusion models say about generative AI's environmental impact? Nicolas Jullien, Robert Viseur Published: 2026-03-22Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E6 / R3 (96%) | 15 |
| KLDrive: Fine-Grained 3D Scene Reasoning for Autonomous Driving based on Knowledge Graph Jingyi Zhang, Onat Gungor, Tajana Rosing, Xiaofan Yu Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E7 / R4 (96%) | - |
| LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning Chao Zhang, Chong Peng, Cunguang Wang, Dengchang Zhao Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E5 / R3 (98%) | - |
| ORACLE: Optimizing Reasoning Abilities of Large Language Models via Constraint-Led Synthetic Data Elicitation Keze Wang, Wentao Wan, Zhuojie Yang Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E7 / R3 (95%) | - |
| Persona Vectors in Games: Measuring and Steering Strategies via Activation Vectors Andrew Zhang, Johnathan Sun Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E4 / R2 (94%) | - |
| PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost Abhibha Gupta, Baihe Huang, Charles Wang, Damon Mosk-Aoyama Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E5 / R3 (96%) | - |
| Revisiting Tree Search for LLMs: Gumbel and Sequential Halving for Budget-Scalable Reasoning Aleksandr Panov, Alexey Skrynnik, Leonid Ugadiarov, Yuri Kuratov Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E6 / R4 (98%) | - |
| RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models Dongyoung Kim, Huiwon Jang, Jaehyung Kim, Jinwoo Shin Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-03-22 | cs.AI | ai-safety, alignment-training, csai, preprint | E7 / R4 (97%) | - |
| Safety as Computation: Certified Answer Reuse via Capability Closure in Task-Oriented Dialogue Cosimo Spera Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E5 / R3 (95%) | - |
| Session Risk Memory (SRM): Temporal Authorization for Deterministic Pre-Execution Safety Gates Florin Adrian Chitan Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E5 / R3 (97%) | - |
| Silent Commitment Failure in Instruction-Tuned Language Models: Evidence of Governability Divergence Across Architectures Gregory M. Ruddell Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E6 / R3 (97%) | - |
| STEM Agent: A Self-Adapting, Tool-Enabled, Extensible Architecture for Multi-Protocol AI Agent Systems Aaron Shen, Alfred Shen Published: 2026-03-22Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E6 / R3 (96%) | - |
| The AI Scientific Community: Agentic Virtual Lab Swarms Ulisses Braga-Neto Published: 2026-03-22Area: cs.AICitations: 22 Tags: ai-safety, csai, preprint | 2026-03-22 | cs.AI | ai-safety, csai, preprint | E5 / R3 (94%) | 22 |