9 citations · 19 across the 24 of their papers we have counts for
3 papers · 1 filter
Automata from Agent Traces: Failure and Next-Step Prediction
Seonglae Cho, Franklin Cardenoso Fernandez, Umar Mohammed +4
LLM-based agents execute multi-step tasks, but their behavioral structure remains opaque: long unstructured traces resist the safety auditing and runtime monitoring that deployment…
NormCode: A Semi-Formal Language for Auditable AI Planning
Xin Guan, Yunshan Li, Zekun Wu +1
As AI systems move into high stakes domains such as legal reasoning, medical diagnosis, and financial decision making, regulators and practitioners increasingly demand auditability…
Bias Amplification: Large Language Models as Increasingly Biased Media
Ze Wang, Zekun Wu, Jeremy Zhang +5
Model collapse, a phenomenon characterized by performance degradation due to iterative training on synthetic data, has been widely studied. However, its implications for bias ampli…