Instructional Text Across Disciplines: A Survey of Representations, Downstream Tasks, and Open Challenges Toward Capable AI Agents

TL;DR

This survey reviews the landscape of complex instruction understanding in NLP, analyzing 181 papers to identify trends, challenges, and future opportunities for deploying large language models as capable AI agents across diverse domains.

Contribution

It provides a comprehensive systematic review of resources, representations, and downstream tasks related to complex instruction understanding, bridging research gaps and highlighting future directions.

Findings

Identified key trends and challenges in instruction understanding.

Analyzed 181 papers to map the research landscape.

Highlighted future research opportunities in complex instruction processing.

Abstract

Recent advances in large language models have demonstrated promising capabilities in following simple instructions through instruction tuning. However, real-world tasks often involve complex, multi-step instructions that remain challenging for current NLP systems. Robust understanding of such instructions is essential for deploying LLMs as general-purpose agents that can be programmed in natural language to perform complex, real-world tasks across domains like robotics, business automation, and interactive systems. Despite growing interest in this area, there is a lack of a comprehensive survey that systematically analyzes the landscape of complex instruction understanding and processing. Through a systematic review of the literature, we analyze available resources, representation schemes, and downstream tasks related to instructional text. Our study examines 181 papers, identifying trends, challenges, and opportunities in this emerging field. We provide AI/NLP researchers with essential background knowledge and a unified view of various approaches to complex instruction understanding, bridging gaps between different research directions and highlighting future research opportunities.