Multilingual Prompt Localization for Agent-as-a-Judge: Language and Backbone Sensitivity in Requirement-Level Evaluation
arXiv:2604.04532v1 Announce Type: new
Abstract: Evaluation language is typically treated as a fixed English default in agentic code benchmarks, yet we show that changing the judge’s language can invert backbone rankings. We localize the Agent-as-a-Jud…