PromptBridge: Cross-Model Prompt Transfer for Large Language Models
Yaxuan Wang · Quan Liu · Zhenting Wang · Zichao Li · Wei Wei · Yang Liu · Yujia Bao
This paper introduces PromptBridge, a training-free method that automatically translates prompts between different LLMs to enable seamless model switching with minimal performance loss.
摘要
Large language model (LLM) systems frequently switch between models due to evolving capabilities, cost, and deployment constraints. However, prompts are highly model-sensitive: prompts engineered for one model often degrade substantially when reused on another. We term this phenomenon \emph{Model Drifting}, and show through extensive empirical analysis that it is common and severe across diverse LLM configurations. To address this, we propose \emph{PromptBridge}, a training-free framework for cross-model prompt transfer that preserves prompt effectiveness under model switches. It uses a set of alignment tasks to calibrate source and target models via \emph{Model-Adaptive Reflective Prompt Evolution (MAP-RPE)}, and learns a prompt mapping that translates a source-model prompt into an optimized target-model prompt without per-task or per-model re-optimization. Experiments across single- and multi-agent benchmarks demonstrate that \emph{PromptBridge} consistently improves downstream performance while reducing migration effort. For instance, when transferring prompts to \texttt{o3}, \emph{PromptBridge} improves accuracy by 27.39% on \textsc{SWE-Bench} and 39.44% on \textsc{Terminal-Bench} over direct transfer, establishing cross-model prompt transfer as a practical requirement for sustainable LLM system development.