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

2026-01-14

AI Summary

Complex software engineering tasks are challenging for a single large language model to accomplish efficiently, necessitating collaborative and specialized approaches. This work presents the first systematic survey of large language model–driven multi-agent systems applied across the software development lifecycle, encompassing critical phases such as requirements engineering, code generation, static analysis, testing, and debugging. It provides an in-depth analysis of agent architectures, communication protocols, and evaluation benchmarks. The study clarifies core challenges including multi-agent coordination, human–AI collaboration, cost optimization, and data collection, while outlining promising directions for future research. By offering a comprehensive landscape and technical roadmap, this survey aims to advance intelligent software engineering in both academia and industry.

Technology Category

• Multiagent Systems: Teamwork
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Large language models for search

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.

Problem

• Large Language Models
• Software Engineering
• Multi-agent Systems
• Software Development Life Cycle
• Agentic Systems

Innovation

• LLM-based multi-agent systems
• Software Development Life Cycle
• Agentic frameworks
• Human-agent coordination
• Computational cost optimization