Autonomous scientific research agents are increasingly applied to end-to-end scientific workflows, including literature review, data analysis, experimentation, and report generation. However, open-ended research tasks often do not clearly specify the analyses, methods, and success criteria required to complete the task. As a result, agents may miss important analyses, use inappropriate methods,…
Recent advances in large reasoning models (LRMs) have shown that reinforcement learning with verifiable rewards (RLVR) can substantially improve reasoning in mathematics and code, where outcomes can…
We propose a lightweight two-stage framework for real-time video anomaly detection. The first stage employs YOLO v11n-pose to detect persons and extract seventeen skeletal keypoints in a single…
When a large language model fails a reasoning task, it is often assumed to lack the underlying capability. However, this conflates a genuine absence of reasoning with a late-stage output bottleneck.
