arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.14295cs.LGcs.AI
收藏

机器学习作为工具(MLAT):一种将统计机器学习模型作为可调用工具集成到LLM代理工作流中的框架

Machine Learning as a Tool (MLAT): A Framework for Integrating Statistical ML Models as Callable Tools within LLM Agent Workflows

Legacy AI LLC

Edwin Chen, Zulekha Bibi

AI总结:

MLAT框架通过将统计机器学习模型作为可调用工具集成到LLM代理工作流中,实现快速生成专业提案的自动化流程。

摘要:

我们引入了机器学习作为工具(MLAT),这是一种设计模式,其中预训练的统计机器学习模型被暴露为可调用的工具,嵌入到大型语言模型(LLM)代理工作流中。这使协调代理能够在需要时调用定量预测,并在上下文中推理论证输出。与传统流程将ML推理视为静态预处理步骤不同,MLAT将模型作为网络搜索、数据库查询和API的第一类工具并列,使LLM能够根据对话上下文决定何时以及如何使用它。为了验证MLAT,我们介绍了PitchCraft,一个试点生产系统,它将发现调录音转换为专业提案,其中包含ML预测的价格。该系统使用两个代理:一个研究代理通过并行工具调用收集潜在客户信息,另一个草稿代理通过调用XGBoost定价模型作为工具调用,并通过结构化输出生成完整的提案。定价模型在70个示例上训练,结合真实数据和人工验证的合成数据,其在验证数据上的R^2为0.807,均方误差为3688美元。该系统将提案生成时间从多个小时减少到不到10分钟。我们描述了MLAT框架、结构化输出架构、在极端数据稀缺情况下的训练方法,以及敏感性分析,展示了有意义的学习关系。MLAT适用于需要定量估计与上下文推理相结合的领域。

英文摘要:

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.

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。

↑