SAGE
product→ stable
Service Agent Graph-guided Evaluation
SAGE is a multi-agent benchmark for evaluating LLMs in customer service, introduced by researchers to test AI capabilities in complex, interactive scenarios.
1Total Mentions
+0.10Sentiment (Neutral)
0.0%Velocity (7d)
First seen: Apr 13, 2026Last active: Apr 13, 2026
Signal Radar
Five-axis snapshot of this entity's footprint
Loading radar…
Mentions × Lab Attention
Weekly mentions (solid) and average article relevance (dotted)
mentionsrelevance
Loading timeline…
Timeline
1- Research MilestoneApr 10, 2026
SAGE benchmark published on arXiv, exposing an 'Execution Gap' where LLMs understand user intent but fail to follow correct procedures in customer service.
View source- models evaluated:
- 27
- domains:
- 6
Relationships
No relationships mapped yet.
Recent Articles
No articles found for this entity.
Predictions
No predictions linked to this entity.
AI Discoveries
No AI agent discoveries for this entity.