A structured multi-agent framework reports 56.2% Pass@1 on HumanEval with Llama 3.1 8B int4, versus 45.4% for one-shot generation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Guided Code Generation with LLMs: A Multi-Agent Framework for Complex Code Tasks
A structured multi-agent framework reports 56.2% Pass@1 on HumanEval with Llama 3.1 8B int4, versus 45.4% for one-shot generation.