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

TL;DR

The paper addresses the challenge of scaling complex software engineering tasks by surveying LLM-based multi-agent systems across the SDLC. It synthesizes architectures, coordination frameworks, and evaluation benchmarks, highlighting how specialized agents, planning-based code generation, and tool integration enable end-to-end SE workflows. Key contributions include a taxonomy of agent roles (requirements, coding, testing, debugging), summaries of representative systems, and a roadmap of methodological and deployment challenges. The work aims to guide researchers and practitioners in model selection, framework adoption, and empirical evaluation, ultimately advancing practical, cooperative AI-assisted software development.

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.