SWE-Together: Evaluating Coding Agents in Interactive User Sessions

SWE-Together: Evaluating Coding Agents in Interactive User Sessions

SWE-Together is a multi-turn coding benchmark created from real user-agent interactions, featuring a reactive LLM simulator to evaluate agents based on both final correctness and i…

Hugging Face · Daily Papers ·Yifan Wu, Zhuokai Zhao · ·▲ 11 upvotes

Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.

Autores: Yifan Wu, Zhuokai Zhao, Songlin Li, Ho Hin Lee, Jiacheng Zhu, Shirley Wu

  • 11 upvotes da comunidade
  • Temas: coding-agent benchmarks, multi-turn benchmark, user-agent coding sessions, repository-level tasks, user simulator, corrective feedback turns

Resumo

Resumo original (em inglês), extraído do paper:

SWE-Together is a multi-turn coding benchmark created from real user-agent interactions, featuring a reactive LLM simulator to evaluate agents based on both final correctness and interaction efficiency.

Onde ler

compartilhar: