Author

Yongxi Zhou

Observed name: Zhou, Yongxi

Institution: Northeastern University

Observed institution: Northeastern University

OpenAlex ID: A5144392323

What Does a Repair Agent Gain from Remembering Its Failure? An Exploratory Study on Real Python Bugs

2026 · Ye, Wenbo, Zhou, Yongxi, et al. · arXiv (Cornell University)

Renegotiable Options Fail to Prevent Hold-Up Between Two Profit-Maximizing Frontier LLM Agents

2026 · Yao, Junwei, Yang, Zike, et al. · arXiv (Cornell University)

Component Translation and Judge-Labelled Refusal: A Multilingual Safety Evaluation

2026 · Zhou, Yongxi, Yao, Junwei, et al. · arXiv (Cornell University)

Evaluating Context Compaction on the Questions That Come Later

2026 · Yao, Junwei, Zhou, Yongxi, et al. · arXiv (Cornell University)

One Confidence Threshold, Unequal Coverage: Language Gaps in Typed Decision Interfaces and How Translating Inputs Reduces Them

2026 · Yao, Junwei, Zhou, Yongxi, et al. · arXiv (Cornell University)

Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts

2026 · Zhou, Yongxi, Ye, Wenbo, et al. · arXiv (Cornell University)

Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity

2026 · Zhou, Yongxi, Yao, Junwei, et al. · arXiv (Cornell University)

How Much Can Repeated Running Buy? A Measured Variance Ceiling for LLM Code Evaluation

2026 · Zhou, Yongxi, Choi, Lai Yun, et al. · arXiv (Cornell University)

Works count: 8

Citation count:

H-index:

I10-index: