A multi-agent LLM framework generates software architecture designs and evaluation reports from requirements, claimed to outperform MetaGPT on architectural completeness.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MAAD: Automate Software Architecture Design through Knowledge-Driven Multi-Agent Collaboration
A multi-agent LLM framework generates software architecture designs and evaluation reports from requirements, claimed to outperform MetaGPT on architectural completeness.