# Agent-S: LLM Agentic workflow to automate Standard Operating Procedures

arXiv: https://arxiv.org/abs/2503.15520 · HTML: https://mlsanity.com/paper/2503.15520/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 10 references that are in the map.
- First posted on arXiv 3 Feb 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 8 of 8)

- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [Empowering Biomedical Discovery with AI Agents](https://mlsanity.com/paper/2404.02831/) (2024)
- [KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph](https://mlsanity.com/paper/2402.11163/) (2024)
- [Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems](https://mlsanity.com/paper/2407.13032/) (2024)
- [RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation](https://mlsanity.com/paper/2402.16667/) (2024)
- [StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows](https://mlsanity.com/paper/2403.11322/) (2024)

## Built on by (most cited first, 10 of 10)

- [How Many Instructions Can LLMs Follow at Once?](https://mlsanity.com/paper/2507.11538/) (2025)
- [Position: The Real Barrier to LLM Agent Usability is Agentic ROI](https://mlsanity.com/paper/2505.17767/) (2025)
- [Batch Query Processing and Optimization for Agentic Workflows](https://mlsanity.com/paper/2509.02121/) (2025)
- [Tools as Continuous Flow for Evolving Agentic Reasoning](https://mlsanity.com/paper/2605.07339/) (2026)
- [ORCA: ORchestrating Causal Agent](https://mlsanity.com/paper/2508.21304/) (2025)
- [POLARIS: Typed Planning and Governed Execution for Agentic AI in Back-Office Automation](https://mlsanity.com/paper/2601.11816/) (2026)
- [Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution](https://mlsanity.com/paper/2607.08960/) (2026)
- [OnlineMate: An LLM-Based Multi-Agent Companion System for Cognitive Support in Online Learning](https://mlsanity.com/paper/2509.14803/) (2025)
- [SOPRAG: Multi-view Graph Experts Retrieval for Industrial Standard Operating Procedures](https://mlsanity.com/paper/2602.01858/) (2026)
- [Entity Resolution in Practice: Lessons from a Self-Serve Pipeline](https://mlsanity.com/paper/2607.26298/) (2026)

## Abstract (arXiv)

AI agents using Large Language Models (LLMs) as foundations have shown promise in solving complex real-world tasks. In this paper, we propose an LLM-based agentic workflow for automating Standard Operating Procedures (SOP). For customer care operations, an SOP defines a logical step-by-step process for human agents to resolve customer issues. We observe that any step in the SOP can be categorized as user interaction or API call, while the logical flow in the SOP defines the navigation. We use LLMs augmented with memory and environments (API tools, user interface, external knowledge source) for SOP automation. Our agentic architecture consists of three task-specific LLMs, a Global Action Repository (GAR), execution memory, and multiple environments. SOP workflow is written as a simple logical block of text. Based on the current execution memory and the SOP, the agent chooses the action to execute; it interacts with an appropriate environment (user/API) to collect observations and feedback, which are, in turn, inputted to memory to decide the next action. The agent is designed to be fault-tolerant, where it dynamically decides to repeat an action or seek input from an external knowledge source. We demonstrate the efficacy of the proposed agent on the three SOPs from the e-commerce seller domain. The experimental results validate the agent's performance under complex real-world scenarios.