EvoClawBench
Explore score history ↗EvoClawBench evaluates whether an agent runtime can convert evidence from its own runs into reusable skills that improve fresh executions. It covers 100 tasks and 502 sub-problems across coding, data, office, security, operations, and domain-document workflows, comparing direct execution, pre-authored skills, and post-run skill summarization.
- Released
- 2026-06-23
- Institutions
- Shanghai Jiao Tong University · Zhejiang University
- Evaluates
- General AI, Language & Knowledge, cs.LG
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
EvoClawBench paper
No reported scores are on record for this benchmark yet.