OBLIVION Benchmark

What is OBLIVION?

Evaluates operational skill unlearning in deployed agents across 88 attack episodes, measuring attack success rate and impact-weighted exposure after…

Released

2026-08-08

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/2608.08264

OBLIVION paper

• Paper https://arxiv.org/abs/2608.08264

Which sources cite OBLIVION?

• OBLIVION

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