MA-SAPO：多智能体推理用于评分感知提示优化
MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization
AI总结：
本文提出MA-SAPO框架，通过多智能体推理将评估结果与针对性改进联系起来，提升提示优化的可解释性和可控性，实验表明其在多个评估指标上优于现有方法。
摘要：
提示优化已成为无需重新训练即可提升大型语言模型（LLMs）性能的实用方法。然而，现有框架将评估视为黑箱，仅依赖结果分数而不解释提示成功或失败的原因。此外，它们涉及重复的试错改进，保持隐含，提供有限的可解释性或可操作的指导。本文提出MA-SAPO：一种新的多智能体推理用于评分感知提示优化框架，将评估结果直接与目标改进联系起来。具体而言，在训练阶段，多个智能体解释评估分数，诊断弱点，并生成具体的修订指令，这些指令被存储为可重用的推理资产。在测试阶段，分析代理检索相关示例和资产，而优化代理应用基于证据的编辑来改进提示及其响应。通过将优化建立在结构化推理上，MA-SAPO确保编辑具有可解释性、可审计性和可控性。在HelpSteer1/2基准测试中，我们的框架在多个评估指标上一致优于单次提示、检索增强生成和先前多智能体方法。
英文摘要：
Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks treat evaluation as a black box, relying solely on outcome scores without explaining why prompts succeed or fail. Moreover, they involve repetitive trial-and-error refinements that remain implicit, offering limited interpretability or actionable guidance for systematic improvement. In this paper, we propose MA-SAPO: a new Multi-Agent Reasoning for Score Aware Prompt Optimization framework that links evaluation outcomes directly to targeted refinements. Specifically, in the Training Phase, multiple agents interpret evaluation scores, diagnose weaknesses, and generate concrete revision directives, which are stored as reusable reasoning assets. In the Test Phase, an analyzer agent retrieves relevant exemplars and assets for a new prompt, and a refiner agent applies evidence-based edits to improve the prompt and its response. By grounding optimization in structured reasoning, MA-SAPO ensures edits are interpretable, auditable, and controllable. Experiments on the HelpSteer1/2 benchmarks show that our framework consistently outperforms single-pass prompting, retrieval-augmented generation, and prior multi-agent methods across multiple evaluation metrics.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
