SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPs
This addresses practical application challenges for AI agents in real-world scenarios by enabling better planning and domain expertise integration, though it appears incremental as it builds on existing agent frameworks with a novel procedural approach.
The paper tackles the limited planning and domain-specific knowledge utilization of general-purpose AI agents by introducing SOP-Agent, a framework that uses natural language Standard Operational Procedures (SOPs) to guide agents, achieving performance superior to general-purpose frameworks and comparable to domain-specific systems across multiple domains.
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.