Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents
🤖 AI Summary
This study addresses the core challenges in transitioning LLM-driven agents from theoretical research to industrial deployment. We propose the first industrial-oriented agent capability maturity framework, systematically characterizing evolutionary trajectories across three technical pillars—memory, planning, and tool use—while integrating multi-agent collaboration, domain-adaptive memory mechanisms, and task-aware planning architectures. To validate cross-domain applicability, we establish an evaluation ecosystem spanning digital engineering, scientific discovery, and embodied intelligence, and design a specialized benchmark emphasizing realism, safety, and industry alignment. Our empirical analysis reveals critical gaps in existing evaluations—particularly regarding robustness in dynamic environments and alignment with domain-specific knowledge. Building on these findings, we advocate an “adaptive socio-technical systems” paradigm for agent evolution and propose concrete co-governance strategies. The framework and benchmark provide both methodological foundations and practical guidance for developing production-grade intelligent agents. (149 words)
Application Category
📝 Abstract
With the rise of large language models (LLMs), LLM agents capable of autonomous reasoning, planning, and executing complex tasks have become a frontier in artificial intelligence. However, how to translate the research on general agents into productivity that drives industry transformations remains a significant challenge. To address this, this paper systematically reviews the technologies, applications, and evaluation methods of industry agents based on LLMs. Using an industry agent capability maturity framework, it outlines the evolution of agents in industry applications, from "process execution systems" to "adaptive social systems." First, we examine the three key technological pillars that support the advancement of agent capabilities: Memory, Planning, and Tool Use. We discuss how these technologies evolve from supporting simple tasks in their early forms to enabling complex autonomous systems and collective intelligence in more advanced forms. Then, we provide an overview of the application of industry agents in real-world domains such as digital engineering, scientific discovery, embodied intelligence, collaborative business execution, and complex system simulation. Additionally, this paper reviews the evaluation benchmarks and methods for both fundamental and specialized capabilities, identifying the challenges existing evaluation systems face regarding authenticity, safety, and industry specificity. Finally, we focus on the practical challenges faced by industry agents, exploring their capability boundaries, developmental potential, and governance issues in various scenarios, while providing insights into future directions. By combining technological evolution with industry practices, this review aims to clarify the current state and offer a clear roadmap and theoretical foundation for understanding and building the next generation of industry agents.
Problem
Research questions and friction points this paper is trying to address.
Translating general LLM agent research into practical industry productivity solutions
Systematically reviewing technologies, applications and evaluation methods for industry agents
Addressing practical challenges and providing roadmap for next-generation industry agents
Innovation
Methods, ideas, or system contributions that make the work stand out.
Memory, Planning, Tool Use enable agent capabilities
Industry agents evolve from execution to adaptive systems
Evaluation benchmarks address authenticity, safety, industry specificity
🔎 Similar Papers
No similar papers found.
