ABRA shows radiology agents excel at tool execution (89%+) but struggle with outcomes (0-25%), with oracle perception raising outcomes to 69-100%, identifying perception as the primary bottleneck.
NEJM AI , volume =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Intent-aware retrieval over assertion-labeled knowledge graphs improves clinical QA accuracy by 22 percentage points on a new MIMIC-IV benchmark that stresses negation, temporality, and attribution.
citing papers explorer
-
ABRA: Agent Benchmark for Radiology Applications
ABRA shows radiology agents excel at tool execution (89%+) but struggle with outcomes (0-25%), with oracle perception raising outcomes to 69-100%, identifying perception as the primary bottleneck.
-
ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IV
Intent-aware retrieval over assertion-labeled knowledge graphs improves clinical QA accuracy by 22 percentage points on a new MIMIC-IV benchmark that stresses negation, temporality, and attribution.