CAPRA is a multi-agent LLM system with evidence anchoring and consistency checking that analyzes software architecture deliverables and meets 88.8% of an eight-criterion evaluation on 10 student reports.
In: Proceedings of the IEEE/ACM International Workshop on New Trends in Software Architecture (SATrends)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CAPRA: Scaling Feedback on Software Architecture Deliverables with a Multi-Agent LLM System
CAPRA is a multi-agent LLM system with evidence anchoring and consistency checking that analyzes software architecture deliverables and meets 88.8% of an eight-criterion evaluation on 10 student reports.