AutoIndex: LLM-Written Code Optimizes Retrieval Indexing

UMass Amherst and Databricks Mosaic Research introduced AutoIndex, which treats indexing and chunking as code optimization, letting LLMs write executable representation programs that boost recall by an average of 8.4% across 8 tasks.

2026-09-14 ~ 2026-09-14 · 3 related posts

• AutoIndex learns document-representation programs, lifting retrieval recall +8.4% on average — CShorten30 · 2026-09-14
• UMass AutoIndex Turns Chunking Into Programs an LLM Writes, Not Configs You Tune — mrdrozdov · 2026-09-14

1 near-duplicate retellings: CShorten30