ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents

ArXi:2605.27240v1 Announce Type: new Memory-augmented language agents are increasingly deployed in affective applications such as emotional, where understanding and responding to users' latent emotional needs is critical. However, existing research often treats memory as a tool for factual retrieval, overlooking its role in shaping users' emotional experiences. In this work, we