Benchmark RadarSovereignNegotiation-Bench
SovereignNegotiation-Bench evaluates personal agents in delegated bargaining scenarios, measuring agreement success alongside user utility, privacy, consent, evidence grounding, concession discipline, escalation, and auditability.
- Released
- 2026-07-02
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Addresses the gap that existing negotiation benchmarks focus on agreement or surplus, potentially overlooking critical user protections in delegated bargaining. Provides a framework for evaluating both strategic and sovereign aspects of personal agents.
Motivation
Personal agents will increasingly negotiate on behalf of users: splitting costs with other personal agents, appealing platform decisions, escalating support disputes, requesting refunds, changing subscriptions, and negotiating deadlines or reimbursements.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.