Saved in:
Bibliographic Details
Main Authors: Ye, Anbang, Ma, Qianran, Chen, Jia, Li, Muqi, Li, Tong, Liu, Fujiao, Mai, Siqi, Lu, Meichen, Bao, Haitao, You, Yang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.09316
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915105468317696
author Ye, Anbang
Ma, Qianran
Chen, Jia
Li, Muqi
Li, Tong
Liu, Fujiao
Mai, Siqi
Lu, Meichen
Bao, Haitao
You, Yang
author_facet Ye, Anbang
Ma, Qianran
Chen, Jia
Li, Muqi
Li, Tong
Liu, Fujiao
Mai, Siqi
Lu, Meichen
Bao, Haitao
You, Yang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_09316
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPs
Ye, Anbang
Ma, Qianran
Chen, Jia
Li, Muqi
Li, Tong
Liu, Fujiao
Mai, Siqi
Lu, Meichen
Bao, Haitao
You, Yang
Artificial Intelligence
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.
title SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPs
topic Artificial Intelligence
url https://arxiv.org/abs/2501.09316