Six multi-agent architectures for LLM code generation on HumanEval form two complexity clusters separated by 50-130%, with no accuracy advantage for the complex cluster.
Enhancing LLM-based code generation with complexity metrics: A feedback-driven approach,
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
-
How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEval
Six multi-agent architectures for LLM code generation on HumanEval form two complexity clusters separated by 50-130%, with no accuracy advantage for the complex cluster.