ESL-Bench supplies 100 synthetic user trajectories and 10,000 queries showing database agents achieve 48-58% accuracy while memory RAG baselines reach only 30-38% on longitudinal health reasoning.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Knowledge graphs should use data-driven hierarchical decay surfaces based on velocity and volatility instead of uniform forgetting curves to better identify currently relevant facts.
citing papers explorer
-
ESL-Bench: An Event-Driven Synthetic Longitudinal Benchmark for Health Agents
ESL-Bench supplies 100 synthetic user trajectories and 10,000 queries showing database agents achieve 48-58% accuracy while memory RAG baselines reach only 30-38% on longitudinal health reasoning.
-
Not All Memories Age the Same: Autodiscovery of Adaptive Decay in Knowledge Graphs
Knowledge graphs should use data-driven hierarchical decay surfaces based on velocity and volatility instead of uniform forgetting curves to better identify currently relevant facts.