用小模型生成动态建议，提升大模型性能
How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models
- 训练小型开放权重模型生成个性化语言建议
- 使GPT-5在税务任务上提升27.4%，减少Gemini任务步数24.6%
- 适合需要定制大模型但无法修改权重的场景
前沿语言模型以黑盒服务形式部署，模型权重不可修改，定制仅限于提示。我们提出顾问模型（Advisor Models），通过训练小型开源模型生成动态、实例相关的自然语言建议，从而增强黑盒前沿模型的能力。顾问模型使GPT-5.2在RuleArena（税务）任务上性能提升27.4%，将Gemini 3 Pro在SWE代理任务中的步骤减少24.6%，并优于静态提示优化器，在个性化适配用户偏好时达到85-100%准确率（对比40-60%）。我们还发现顾问模型具备可迁移性：用低成本学生模型训练的顾问仍能提升前沿模型表现。此外，顾问模型具有鲁棒性：在未训练的基准上无性能下降。该方法为黑盒前沿模型提供了实用且低成本的参数化优化路径。
原文摘要 · Abstract (English)
Frontier language models are deployed as black-box services, where model weights cannot be modified and customization is limited to prompting. We introduce Advisor Models, a method to train small open-weight models to generate dynamic, per-instance natural language advice that improves the capabilities of black-box frontier models. Advisor Models improve GPT-5.2's performance on RuleArena (Taxes) by 27.4%, reduce Gemini 3 Pro's steps taken in SWE agent tasks by 24.6%, and outperform static prompt optimizers in personalizing GPT-5 to user preferences (85-100% vs. 40-60%). We also find that advisors are transferable: an advisor trained with a low-cost student model still transfers improvements to a frontier model. Moreover, Advisor Models are robust: we observe no degradation on other benchmarks than the pipeline is trained on. Our method shows how to perform parametric optimization for black-box frontier models in a practical and cost-effective way.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。