6 papers
Agentic Safety is an Epistemic Property, Not a Behavioral One
Charles L. Wang, Keir Dorchen, Peter Jin
Contemporary AI safety spans pre-training interventions, post-training alignment, deployment-time controls, monitoring, and red-teaming. These methods are necessary, but they prima…
HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?
Tu Trinh, Mohamed Elfeki, Guangze Luo +9
Frontier coding agents solve complex tasks when given complete context but collapse when specifications are incomplete or ambiguous. The bottleneck is not raw capability, but judgm…
On The Statistical Limits of Self-Improving Agents
Charles L. Wang, Keir Dorchen, Peter Jin
We develop a learning-theoretic framework for analyzing self-improving agents by decomposing self-modification into five axes. Within this framework, we prove a sharp boundary: und…
MathBode: Measuring the Stability of LLM Reasoning using Frequency Response
Charles L. Wang
This paper presents MathBode, a dynamic diagnostic for mathematical reasoning in large language models (LLMs). Instead of one-shot accuracy, MathBode treats each parametric problem…
MI9: An Integrated Runtime Governance Framework for Agentic AI
Charles L. Wang, Trisha Singhal, Ameya Kelkar +1
Agentic AI systems capable of reasoning, planning, and executing actions present fundamentally distinct governance challenges compared to traditional AI models. Unlike conventional…
Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning
Ang Li, Charles Wang, Deqing Fu +9
Humans often use visual aids, for example diagrams or sketches, when solving complex problems. Training multimodal models to do the same, known as Visual Chain of Thought (Visual C…