Paper
LLMs & Texto
To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair
LLM-based program repair agents frequently use execution-based testing but show inconsistent efficiency, with execution costs outweighing benefits in many cases.
Hugging Face · Daily Papers
·Zhihao Lin, Junhua Zhu
·
·▲ 1 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Zhihao Lin, Junhua Zhu, Mingyi Zhou, Xin Wang, Zhensu Sun, Renyu Yang
- 1 upvotes da comunidade
- Temas: generate-run-revise paradigm, LLM-based agents, program repair, execution-based approach, SWE-bench, agent traces
Resumo
Resumo original (em inglês), extraído do paper:
LLM-based program repair agents frequently use execution-based testing but show inconsistent efficiency, with execution costs outweighing benefits in many cases.Onde ler
// relacionados