A multi-agent LLM framework generates software architecture designs and evaluation reports from requirements, claimed to outperform MetaGPT on architectural completeness.
LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 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.