READ, a deterministic grep-outline-read agent over a raw financial PDF, answers 58.8% of 51 verified questions versus 15.7% for dense top-k retrieval, and the gain sits in the interface, not the iteration loop.
Title resolution pending
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
-
Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
READ, a deterministic grep-outline-read agent over a raw financial PDF, answers 58.8% of 51 verified questions versus 15.7% for dense top-k retrieval, and the gain sits in the interface, not the iteration loop.