Author

Yuhong Ge

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Aug 2026

Coverage, Not Credit: Failure-Credit Routing of Zeroth-Order Perturbation Budgets Does Not Improve On-Pool Sample Efficiency for LLM Agents

This study reports three failure modes that can silently invalidate ZO/ES experiments on frozen LLMs and finds no statistically detectable improvement over uniform allocation in any on-pool comparison in any on-pool comparison.

Yuhong Ge · 1 citation