SEW automatically generates and self-evolves multi-agent workflows for code generation, yielding up to 12% gains on LiveCodeBench over the base LLM.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
SEW: Self-Evolving Agentic Workflows for Automated Code Generation
SEW automatically generates and self-evolves multi-agent workflows for code generation, yielding up to 12% gains on LiveCodeBench over the base LLM.