arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.09316cs.AI
收藏

SOP-Agent:赋予通用AI智能体领域特定SOP能力

SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPs

HPC-AI Tech(HPC-AI科技);Grab Holdings Inc(Grab控股公司);National University of Singapore(新加坡国立大学)

Anbang Ye, Qianran Ma, Jia Chen, Muqi Li, Tong Li, Fujiao Liu, Siqi Mai, Meichen Lu, Haitao Bao, Yang You

AI总结:

针对通用AI智能体规划能力不足、难用领域知识的问题,提出SOP-agent框架,以自然语言伪代码式SOP的决策图引导任务执行,多领域实验性能优于通用框架、媲美领域专用系统,还推出首个客户服务落地决策基准。

摘要:

尽管通用AI智能体已取得显著进展,但仍有若干挑战阻碍其在真实场景中的实际应用。首先,大语言模型(LLM)有限的规划能力限制了AI智能体有效解决需要长时程规划的复杂任务。其次,通用AI智能体难以高效利用领域特定知识与人类专业经验。本文提出标准操作流程引导智能体(SOP-agent),这是一种通过自然语言编写的伪代码风格标准操作流程(SOPs)构建领域特定智能体的新型框架。形式上,我们将SOP表示为决策图,通过遍历该图引导智能体完成SOP所规定的任务。我们在多个领域的任务上开展了广泛实验,涵盖决策、搜索与推理、代码生成、数据清洗以及落地式客户服务。SOP-agent展现出出色的通用性,性能优于通用智能体框架,且与领域特定智能体系统相当。此外,我们提出了Grounded Customer Service Benchmark(落地式客户服务基准),这是首个基于SOP评估AI智能体在客户服务场景中落地决策能力的基准。

英文摘要:

Despite significant advancements in general-purpose AI agents, several challenges still hinder their practical application in real-world scenarios. First, the limited planning capabilities of Large Language Models (LLM) restrict AI agents from effectively solving complex tasks that require long-horizon planning. Second, general-purpose AI agents struggle to efficiently utilize domain-specific knowledge and human expertise. In this paper, we introduce the Standard Operational Procedure-guided Agent (SOP-agent), a novel framework for constructing domain-specific agents through pseudocode-style Standard Operational Procedures (SOPs) written in natural language. Formally, we represent a SOP as a decision graph, which is traversed to guide the agent in completing tasks specified by the SOP. We conduct extensive experiments across tasks in multiple domains, including decision-making, search and reasoning, code generation, data cleaning, and grounded customer service. The SOP-agent demonstrates excellent versatility, achieving performance superior to general-purpose agent frameworks and comparable to domain-specific agent systems. Additionally, we introduce the Grounded Customer Service Benchmark, the first benchmark designed to evaluate the grounded decision-making capabilities of AI agents in customer service scenarios based on SOPs.

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。

↑