Benchmark RadarAI BENCHMARK PROFILE
SovereignPA-Bench
SovereignPA-Bench evaluates user-owned personal agents on 120 sovereignty stress scenarios, measuring task success, alignment, privacy, consent, evidence, manipulation, burden, and auditability in evolving intent and platform mediation contexts.
- Released
- 2026-07-06
- Readiness
- Paper only
- Primary field
- Robotics & Autonomous Systems
Why it matters
Personal agents must balance task completion with user sovereignty. This benchmark quantifies trade-offs across privacy, consent, and manipulation, enabling principled agent design.
Motivation
Personal agents are becoming persistent user-owned intermediaries: they remember preferences, filter platform-mediated information, use tools, and negotiate with services.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.