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.
Codesystem: Unified code for units of measure (ucum)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
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.