SOP-Maze: Evaluating Large Language Models on Complicated Business Standard Operating Procedures

ACL ARR 2026 January Submission4060 Authors

Keywords: Large Language Models, Instruction Following, Standard Operating Procedures (SOPs), Benchmarking, Business AI, Logical Reasoning, Fully Human-annotated Benchmark

Abstract:

As large language models (LLMs) are widely deployed as domain-specific agents, many benchmarks have been proposed to evaluate their ability to follow instructions and make decisions in real-world scenarios.
However, business scenarios often involve complex standard operating procedures (SOPs), and the evaluation of LLM capabilities in such contexts has not been fully explored. To bridge this gap, we propose SOP-Maze, a benchmark constructed from real-world business data and adapted into a collection of 397 instances and 3422 subtasks from 23 complex SOP scenarios. We further categorize SOP tasks into two broad classes: Lateral Root System (LRS), representing wide-option tasks that demand precise selection; and Heart Root System (HRS), which emphasizes deep logical reasoning with complex branches. Extensive experiments reveal that nearly all state-of-the-art models struggle with SOP-Maze. We conduct a comprehensive analysis and identify three key error categories: (i) route blindness: difficulty following procedures; (ii) conversational fragility: inability to handle real dialogue nuances; and (iii) calculation errors: mistakes in time or arithmetic reasoning under complex contexts. The systematic study explores LLM performance across SOP tasks that challenge both breadth and depth, offering new insights for improving model capabilities. We have open-sourced our work on the anonymous link: https://anonymous.4open.science/r/SOP-Maze.

Paper Type: Long

Research Area: Resources and Evaluation

Research Area Keywords: Language Modeling,Interpretability and Analysis of Models for NLP,Human-Centered NLP

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Reproduction study, Approaches to low-resource settings, Publicly available software and/or pre-trained models, Data resources, Data analysis

Languages Studied: English,Chinese

Submission Number: 4060