FIELD NOTES TOPIC
data retrieval
3 notes, newest first.
Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
The authors propose a new method for document search called READ (Reliable Embedding-free Agentic Document-search). This method uses an interpretable agent that performs three operations: normalized lexical search…
Comparative Approaches to Agent Retrieval over Large Skill Libraries
The study compares two systems for deciding which skills to load from large skill libraries in AI agents. The first system is a hybrid ranker that combines lexical and dense-embedding retrieval for sparse, on-demand…
Field Order Should Not Matter: Permutation-Invariant Embedding Model Fine-Tuning for Structured Metadata Retrieval
Researchers propose a method called permutation-invariant fine-tuning (PI-FT) to improve structured metadata retrieval. They show that the choice of field order in a record can significantly impact retrieval quality…
