A Unified Evaluation-Instructed Framework for Query-Dependent Prompt Optimization

ArXi:2511.19829v2 Announce Type: replace Most prompt-optimization methods refine a single static template, making them ineffective in complex and dynamic user scenarios. Existing query-dependent approaches rely on unstable textual feedback or black-box reward models, providing weak and uninterpretable optimization signals. fundamentally, prompt quality itself lacks a unified, systematic definition, resulting in fragmented and unreliable evaluation signals. Our approach first establishes a performance-oriented, systematic, and comprehensive prompt evaluation framework.