Pith. sign in

REVIEW 4 cited by

Software Architecture Meets LLMs: A Systematic Literature Review

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2505.16697 v1 pith:XUOMGUZR submitted 2025-05-22 cs.SE

classification cs.SE
keywords architecturesoftwarellmsdesigntasksapproachesresearchtechniques
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) are used for many different software engineering tasks. In software architecture, they have been applied to tasks such as classification of design decisions, detection of design patterns, and generation of software architecture design from requirements. However, there is little overview on how well they work, what challenges exist, and what open problems remain. In this paper, we present a systematic literature review on the use of LLMs in software architecture. We analyze 18 research articles to answer five research questions, such as which software architecture tasks LLMs are used for, how much automation they provide, which models and techniques are used, and how these approaches are evaluated. Our findings show that while LLMs are increasingly applied to a variety of software architecture tasks and often outperform baselines, some areas, such as generating source code from architectural design, cloud-native computing and architecture, and checking conformance remain underexplored. Although current approaches mostly use simple prompting techniques, we identify a growing research interest in refining LLM-based approaches by integrating advanced techniques.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Verified LLM-Driven Synthesis for Concept Design

    cs.SE 2026-07 conditional novelty 7.0 of 10

    A formal reaction semantics plus an LLM+Alloy CEGIS loop synthesizes and bounded-verifies coordination rules for Concept Design, with scenarios beating natural-language prompts for intent recovery.

  2. Large Language Models for Software Engineering Diagrams: A Systematic Review of UML and ER modelling

    cs.SE 2026-07 conditional novelty 5.0 of 10

    A systematic review of 64 papers finds LLM research on software diagrams is concentrated on UML class-diagram generation, dominated by GPT models, and held back by weak evaluation and scarce shared benchmarks.

  3. MAAD: Automate Software Architecture Design through Knowledge-Driven Multi-Agent Collaboration

    cs.SE 2025-07 conditional novelty 5.0 of 10

    A multi-agent LLM framework generates software architecture designs and evaluation reports from requirements, claimed to outperform MetaGPT on architectural completeness.

  4. Adoption of Generative Artificial Intelligence in the German Software Engineering Industry: An Empirical Study

    cs.SE 2026-01 conditional novelty 4.0 of 10

    In a survey of 109 German developers plus 18 interviews, GenAI productivity gains cluster among 'power users'; junior and senior developers perceive prompting differently, and limited codebase context is a major barrier.

Pith tools