| InfEngine: A Self-Verifying and Self-Optimizing Intelligent Engine for Infrared Radiation Computing | cs.AI | 0 | Open |
| AMV-L: Lifecycle-Managed Agent Memory for Tail-Latency Control in Long-Running LLM Systems | cs.AI | 0 | Open |
| Quantifying Automation Risk in High-Automation AI Systems: A Bayesian Framework for Failure Propagation and Optimal Oversight | cs.AI | 0 | Open |
| Pavement Missing Condition Data Imputation through Collective Learning-Based Graph Neural Networks | cs.AI | 0 | Open |
| Benchmark Test-Time Scaling of General LLM Agents | cs.AI | 0 | Open |
| MagicAgent: Towards Generalized Agent Planning | cs.AI | 0 | Open |
| Learning to Detect Language Model Training Data via Active Reconstruction | cs.AI | 0 | Open |
| An interpretable framework using foundation models for fish sex identification | cs.AI | 0 | Open |
| Routing-Aware Explanations for Mixture of Experts Graph Models in Malware Detection | cs.AI | 0 | Open |
| Pushing the Limits of Inverse Lithography with Generative Reinforcement Learning | cs.AI | 0 | Open |
| A Markovian View of Iterative-Feedback Loops in Image Generative Models: Neural Resonance and Model Collapse | cs.AI | 0 | Open |
| Unsupervised Denoising of Diffusion-Weighted Images with Bias and Variance Corrected Noise Modeling | cs.AI | 0 | Open |
| OpenPort Protocol: A Security Governance Specification for AI Agent Tool Access | cs.AI | 0 | Open |
| Grouter: Decoupling Routing from Representation for Accelerated MoE Training | cs.AI | 0 | Open |
| Agentic Problem Frames: A Systematic Approach to Engineering Reliable Domain Agents | cs.AI | 0 | Open |