EvoClawBench

What is EvoClawBench?

EvoClawBench evaluates whether an agent runtime can convert evidence from its own runs into reusable skills that improve fresh executions. It covers 100 tasks…

Released

2026-06-23

Evaluates

General AI, Language & Knowledge, cs.LG

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.09711

EvoClawBench paper

• Paper https://arxiv.org/abs/2607.09711

Which sources cite EvoClawBench?

• EvoClawBench

Related General AI, Language & Knowledge, cs.LG benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench