让预训练模型像工具一样被大模型调用,实现智能决策与定量预测结合。
Machine Learning as a Tool (MLAT): A Framework for Integrating Statistical ML Models as Callable Tools within LLM Agent Workflows
- 将统计机器学习模型封装为可调用工具,嵌入大模型工作流中
- 定价模型在70个样本上达到R²=0.807,误差3688美元,提案生成时间缩短至10分钟内
- 适合需要定量估算与上下文推理结合的场景,如商业提案自动化
我们提出机器学习即工具(MLAT)框架,将预训练的统计机器学习模型作为可调用工具集成到大语言模型(LLM)代理工作流中。该设计使代理能在需要时调用量化预测,并在上下文中推理输出结果。与传统将模型推理视为静态预处理的流程不同,MLAT将模型视为与网络搜索、数据库查询和API同等地位的一等工具,使大模型可根据对话上下文自主决定使用时机与方式。为验证该框架,我们构建了PitchCraft系统,将发现通话录音转化为专业提案,其中包含由XGBoost模型预测的定价。该系统由研究代理(并行调用工具获取客户情报)和起草代理(调用定价模型并生成结构化提案)组成。定价模型基于70个真实与人工验证合成数据样本训练,在保留数据上获得R²=0.807,平均绝对误差为3688美元。系统将提案生成时间从数小时压缩至10分钟以内。我们还描述了MLAT框架、结构化输出架构、极端数据稀缺下的训练方法及敏感性分析,证明了模型能学习到有意义的关系。该方法可推广至需结合定量估计与上下文推理的领域。
原文摘要 · Abstract (English)
We introduce Machine Learning as a Tool (MLAT), a design pattern in which pre-trained statistical machine learning models are exposed as callable tools within large language model (LLM) agent workflows. This allows an orchestrating agent to invoke quantitative predictions when needed and reason about their outputs in context. Unlike conventional pipelines that treat ML inference as a static preprocessing step, MLAT positions the model as a first-class tool alongside web search, database queries, and APIs, enabling the LLM to decide when and how to use it based on conversational context. To validate MLAT, we present PitchCraft, a pilot production system that converts discovery call recordings into professional proposals with ML-predicted pricing. The system uses two agents: a Research Agent that gathers prospect intelligence via parallel tool calls, and a Draft Agent that invokes an XGBoost pricing model as a tool call and generates a complete proposal through structured outputs. The pricing model, trained on 70 examples combining real and human-verified synthetic data, achieves R^2 = 0.807 on held-out data with a mean absolute error of 3688 USD. The system reduces proposal generation time from multiple hours to under 10 minutes. We describe the MLAT framework, structured output architecture, training methodology under extreme data scarcity, and sensitivity analysis demonstrating meaningful learned relationships. MLAT generalizes to domains requiring quantitative estimation combined with contextual reasoning.
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。