Benchmark
CogManip Benchmark
What is CogManip?
Evaluates 15 manipulative behavior strategies in 1,000 multi-turn LLM interaction scenarios. Benchmark Radar tracks CogManip, cited by 1 source documents, with…
- Released
- 2026-06-04
- Evaluates
- Robot manipulation, Robotics, Robotics & Embodied AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2606.06099
CogManip paper
No reported scores are on record for this benchmark yet.