LLM-Based Agentic Systems for Software Engineering: Challenges and Opportunities

TL;DR

This paper reviews the emerging use of LLM-based multi-agent systems in software engineering, discussing applications, challenges, and future research directions across the SDLC to enhance collaboration and efficiency.

Contribution

It systematically analyzes the current state, challenges, and opportunities of LLM-based agentic systems in software engineering, providing a comprehensive overview for researchers and practitioners.

Findings

Identification of key challenges in multi-agent orchestration and human-agent coordination.

Analysis of current SE evaluation benchmarks and frameworks.

Outline of future research opportunities in data collection and cost optimization.

Abstract

Despite recent advancements in Large Language Models (LLMs), complex Software Engineering (SE) tasks require more collaborative and specialized approaches. This concept paper systematically reviews the emerging paradigm of LLM-based multi-agent systems, examining their applications across the Software Development Life Cycle (SDLC), from requirements engineering and code generation to static code checking, testing, and debugging. We delve into a wide range of topics such as language model selection, SE evaluation benchmarks, state-of-the-art agentic frameworks and communication protocols. Furthermore, we identify key challenges and outline future research opportunities, with a focus on multi-agent orchestration, human-agent coordination, computational cost optimization, and effective data collection. This work aims to provide researchers and practitioners with valuable insights into the current forefront landscape of agentic systems within the software engineering domain.