AutoIndex learns retrieval indexing programs and lifts Recall@100 by 8.4%

Sam O'Nuallain · hf · 2026-07-23

AutoIndex learns retrieval preprocessing as executable programs

AutoIndex treats document representation as an optimization target instead of a fixed preprocessing step. It searches over representation programs—executable transforms that can slice, enrich, normalize, reweight, or reorganize documents before they are indexed.

Results:

The authors argue that document representation should be explicitly optimized, not hard-coded before retrieval starts. Code is available on GitHub.

Related event: AutoIndex Framework Proposes New Paradigm of Representation Program Optimization(8 posts)→

Original post →

More from coding & agent

coding & agent channel →