Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Ke, Zhou, Yufei, Zhang, Xitong, Wang, Haohan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909617419714560
author Chen, Ke
Zhou, Yufei
Zhang, Xitong
Wang, Haohan
author_facet Chen, Ke
Zhou, Yufei
Zhang, Xitong
Wang, Haohan
contents Automatic prompt generation plays a crucial role in enabling general-purpose multi-agent systems to perform diverse tasks autonomously. Existing methods typically evaluate prompts based on their immediate task performance, overlooking the intrinsic qualities that determine their reliability. This outcome-centric view not only limits interpretability but also fails to account for the inherent stochasticity of large language models (LLMs). In this work, we bring attention to prompt stability-the consistency of model responses across repeated executions-as a key factor for building robust and effective prompt generation systems. To quantify this, we propose semantic stability as a criterion for assessing the response consistency of prompts, and fine-tune a LLaMA-based evaluator to measure it automatically across tasks. These components have enabled us to develop the first stability-aware general-purpose prompt generation system that leverages stability feedback to iteratively enhance both prompt quality and system-level performance. Furthermore, we establish a logical chain between prompt stability and task success by analyzing the structural dependencies within our system, proving stability as a necessary condition for effective system-level execution. Empirical results across general and domain-specific tasks demonstrate that our stability-aware framework improves both accuracy and output consistency. By shifting the focus from one-off results to persistent reliability, our work offers a new perspective on prompt design and contributes practical tools for building more trustworthy general-purpose systems.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13546
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems
Chen, Ke
Zhou, Yufei
Zhang, Xitong
Wang, Haohan
Artificial Intelligence
Computation and Language
Multiagent Systems
Automatic prompt generation plays a crucial role in enabling general-purpose multi-agent systems to perform diverse tasks autonomously. Existing methods typically evaluate prompts based on their immediate task performance, overlooking the intrinsic qualities that determine their reliability. This outcome-centric view not only limits interpretability but also fails to account for the inherent stochasticity of large language models (LLMs). In this work, we bring attention to prompt stability-the consistency of model responses across repeated executions-as a key factor for building robust and effective prompt generation systems. To quantify this, we propose semantic stability as a criterion for assessing the response consistency of prompts, and fine-tune a LLaMA-based evaluator to measure it automatically across tasks. These components have enabled us to develop the first stability-aware general-purpose prompt generation system that leverages stability feedback to iteratively enhance both prompt quality and system-level performance. Furthermore, we establish a logical chain between prompt stability and task success by analyzing the structural dependencies within our system, proving stability as a necessary condition for effective system-level execution. Empirical results across general and domain-specific tasks demonstrate that our stability-aware framework improves both accuracy and output consistency. By shifting the focus from one-off results to persistent reliability, our work offers a new perspective on prompt design and contributes practical tools for building more trustworthy general-purpose systems.
title Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems
topic Artificial Intelligence
Computation and Language
Multiagent Systems
url https://arxiv.org/abs/2505.13546