A hybrid ranker outperforms a typed knowledge graph for skill retrieval, because the graph's edges are generated from the same embedding neighborhood the ranker already uses, limiting the graph to the ranker's own candidate set.
Diagnosing and Mitigating Retrieval Bottlenecks in
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Comparative Approaches to Agent Retrieval over Large Skill Libraries
A hybrid ranker outperforms a typed knowledge graph for skill retrieval, because the graph's edges are generated from the same embedding neighborhood the ranker already uses, limiting the graph to the ranker's own candidate set.