AdvPlan-Bench
Explore score history ↗AdvPlan-Bench is an offline benchmark for adversarial evaluation of structured plan-generation agents. It uses typed action chains, adversarial response sets, selector diagnostics, and metrics like BLUE-vs-RED advantage and Nash-gap. Includes 150 synthetic scenarios across five planning templates.
- Released
- 2026-08-01
- Institutions
- Cornell University · Stevens Institute of Technology
- Evaluates
- General AI, Language & Knowledge, cs.LG
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
AdvPlan-Bench paper
No reported scores are on record for this benchmark yet.