LLM-Powered AI Agent Systems and Their Applications in Industry 요약

2025년 5월 22일, arXiv 공개

Abstract—The emergence of Large Language Models (LLMs) has reshaped agent systems. Unlike traditional rule-based agents with limited task scope, LLM-powered agents offer greater flexibility, cross-domain reasoning, and natural language interaction. Moreover, with the integration of multi-modal LLMs, current agent systems are highly capable of processing diverse data modalities, including text, images, audio, and structured tabular data, enabling richer and more adaptive real-world behavior. This paper comprehensively examines the evolution of agent systems from the pre-LLM era to current LLM-powered architectures. We categorize agent systems into software-based, physical, and adaptive hybrid systems, highlighting applications across customer service, software development, manufacturing automation, personalized education, financial trading, and healthcare. We further discuss the primary challenges posed by LLM-powered agents, including high inference latency, output uncertainty, lack of evaluation metrics, and security vulnerabilities, and propose potential solutions to mitigate these concerns.

INTRODUCTION

이 논문은 산업 중신 관점에서 LLM 기반 에이전트 시스템을 개발하고 분류하는 것에 대한 통찰을 제공한다.

AGENT SYSTEMS OVERVIEW

1. Agent Systems Before LLM era

2. LLM-powered Agent System
   LLM 기반 에이전트는 높은 추론 지연, 표준화된 벤치마크와 평가 지표, 보안 문제와 같은 과제에 직면했다.

3. Architecture of LLM-Powered Agent System

INDUSTRY APPLICATIONS

시스템 설계와 산업 적용에 대한 부분은 충분히 탐구되지 않았다.

1. Chatbot: Live Custormer Service

2. Software Development

3. Manufacturing Automation

4. Personalized Education

5. Healthcare

6. Financial Trading

CHALLENGES

1. High Inference Latency

2. Uncertainty of LLM Output

3. Lack of Benchmarks and Evaluation Metrics

4. Security and Privacy Concerns