LLM Agents Factory: Retrieval of Domain-Specific LLM Agents

LLM Agents Factory：领域特定大语言模型智能体的检索

Abstract: Large language model (LLM) agents improve task performance by decomposing problems into role-specialized behaviors. However, their practical deployment is often limited by the computational cost and instability associated with the on-the-fly agent design for each user request.

摘要： 大语言模型（LLM）智能体通过将问题分解为角色专业化的行为，从而提升了任务执行性能。然而，其实际部署往往受到针对每个用户请求进行即时智能体设计所带来的计算成本和不稳定性限制。

To address this, we present LLM Agents Factory, a retrieval-based framework that constructs domain-specific and Wikipedia-grounded agents on demand using a base of over 20K predetermined agent profiles. Our framework supports two modes: (1) agent profile retrieval via semantic search and (2) distillation into a compact model fine-tuned for direct agent generation.

为了解决这一问题，我们提出了 LLM Agents Factory，这是一个基于检索的框架，利用超过 2 万个预设智能体配置库，按需构建领域特定且基于维基百科知识的智能体。我们的框架支持两种模式：（1）通过语义搜索进行智能体配置检索；（2）蒸馏至一个经过微调的紧凑模型，用于直接生成智能体。

Experiments on MMLU, BIG-bench, and BIG-bench Hard in a single-agent scenario demonstrate that our retrieval-based agent construction surpasses non-agent baselines in accuracy while matching AutoGen generation quality with a 120B backbone at a substantially lower inference cost.

在单智能体场景下，针对 MMLU、BIG-bench 和 BIG-bench Hard 的实验表明，我们基于检索的智能体构建方法在准确性上超过了非智能体基准，同时在推理成本大幅降低的情况下，达到了与 120B 主干模型相当的 AutoGen 生成质量。

Our work reveals that retrieval from a structured agent repository provides a cost-efficient, accurate, and controllable alternative to dynamic agent generation, responding to the strict demands of industrial applications. We provide the implementation code and the agent base in this https URL.

我们的研究表明，从结构化智能体库中进行检索，为动态智能体生成提供了一种成本高效、准确且可控的替代方案，能够满足工业应用的严格需求。我们已在 此链接 提供了实现代码和智能体库。