SkillEvolBench

What is SkillEvolBench?

SkillEvolBench evaluates whether LLM agents can distill episodic experience into reusable procedural skills. It includes 180 tasks across six environments…

Released

2026-05-22

Evaluates

General AI, Language & Knowledge, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2605.24117

SkillEvolBench paper

• Paper https://arxiv.org/abs/2605.24117

Which sources cite SkillEvolBench?

• SkillEvolBench

Related General AI, Language & Knowledge, cs.AI 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