Benchmark
AdvPlan-Bench
What is AdvPlan-Bench?
AdvPlan-Bench is an offline benchmark for adversarial evaluation of structured plan-generation agents. It uses typed action chains, adversarial response sets…
- Released
- 2026-08-01
- 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/2608.00832
AdvPlan-Bench paper
No reported scores are on record for this benchmark yet.