2 papers
cs.LG2026
PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety
Ding Jia, Wei Liu, Xianglong Du +5
The transition from Large Language Models (LLMs) to agents shifts safety stakes from toxic text to irreversible environmental harm. While current defenses remain largely retrospect…
cs.AI2026
When Sample Selection Bias Precipitates Model Collapse
Xinbao Qiao, Xianglong Du, Wei Liu +4
The proliferation of recursive training on synthetic data can alleviate data scarcity but risks model collapse, where repeated training erodes distributional tails and homogenizes…