Story
arxiv_cs_cl · Nov 3, 2026 · paper
Source brief
One Assistant, Many Memories: Benchmarking Real-World Group Assistance When Recall Is Not Enough
arxiv.orgNov 3, 2026
original source linked
In brief
The value of memory lies not only in recall but in using it to provide appropriate assistance. Recent benchmarks test memory use in personalisation and agentic tasks, but seldom evaluate assistance without fixed answe...
Feed lens
agenticevaluation