A Survey on Agent Workflow -- Status and Future

TL;DR

This survey reviews the current state and future directions of agent workflow systems, emphasizing their architecture, capabilities, challenges, and open research problems in the context of autonomous AI agents and large language models.

Contribution

It provides a comprehensive classification and comparison of over 20 agent workflow systems, highlighting patterns, challenges, and future research opportunities.

Findings

Identification of common architectural patterns

Analysis of technical challenges in workflow scalability and security

Outline of open problems like standardization and multimodal integration

Abstract

In the age of large language models (LLMs), autonomous agents have emerged as a powerful paradigm for achieving general intelligence. These agents dynamically leverage tools, memory, and reasoning capabilities to accomplish user-defined goals. As agent systems grow in complexity, agent workflows-structured orchestration frameworks-have become central to enabling scalable, controllable, and secure AI behaviors. This survey provides a comprehensive review of agent workflow systems, spanning academic frameworks and industrial implementations. We classify existing systems along two key dimensions: functional capabilities (e.g., planning, multi-agent collaboration, external API integration) and architectural features (e.g., agent roles, orchestration flows, specification languages). By comparing over 20 representative systems, we highlight common patterns, potential technical challenges, and emerging trends. We further address concerns related to workflow optimization strategies and security. Finally, we outline open problems such as standardization and multimodal integration, offering insights for future research at the intersection of agent design, workflow infrastructure, and safe automation.