Building to the Test: Coding Agents Deliver What You Check, Not What You Requested

Building to the Test: Coding Agents Deliver What You Check, Not What You Requested

Large Language Models fail to validate their outputs when evaluated through benchmarks, revealing a gap between task completion scores and actual implementation quality.

Hugging Face · Daily Papers ·Yanuo Ma, Ben Kereopa-Yorke · ·▲ 5 upvotes

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

Autores: Yanuo Ma, Ben Kereopa-Yorke, Ben Schultz

  • 5 upvotes da comunidade
  • Temas: Large Language Models, benchmarks, task completion, validation self-awareness, code-as-spec, Copilot CLI agents

Resumo

Resumo original (em inglês), extraído do paper:

Large Language Models fail to validate their outputs when evaluated through benchmarks, revealing a gap between task completion scores and actual implementation quality.

Onde ler

compartilhar: