EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions
EnterpriseClawBench presents a benchmark for enterprise agents based on real-world sessions with 852 reproducible tasks, emphasizing comprehensive evaluation metrics beyond single…
Hugging Face · Daily Papers
·Jincheng Zhong, Weizhi Wang
·
·▲ 55 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Jincheng Zhong, Weizhi Wang, Che Jiang, Kai Tian, Zhenzhao Yuan, Junlin Yang
- 55 upvotes da comunidade
- Temas: enterprise agent benchmark, reproducible tasks, workplace sessions, harness--model combinations, artifact delivery, skill-transfer behavior
Resumo
Resumo original (em inglês), extraído do paper:
EnterpriseClawBench presents a benchmark for enterprise agents based on real-world sessions with 852 reproducible tasks, emphasizing comprehensive evaluation metrics beyond single performance scores.
