Benchmark Radar
AI BENCHMARK PROFILE

ENPMR-Bench

General AIKnowledge & ReasoningSearch & Retrieval

Benchmark for emotional need-aware proactive memory retrieval in support agents, with 1,800+ dialogues mapped to Maslow's hierarchy.

Released
2026-05-26
Readiness
Paper only
Primary field
General AI

Why it matters

Current memory retrieval is factual, neglecting emotional needs. ENPMR-Bench evaluates proactive retrieval for empathetic interaction.

Motivation

Memory-augmented language agents are increasingly deployed in affective applications such as emotional support, where understanding and responding to users' latent emotional needs is critical.

Primary resources

Benchmark Radar records only publicly supported details and links back to primary sources for verification.