SELF-INDEX: a framework for retrieval indexes that self-evolve without humans

Sangam Lee · hf · 2026-09-19

SELF-INDEX is a framework enabling retrieval indexes to self-evolve without human intervention. Its Optimizer autonomously diagnoses retrieval shortfalls, selectively revises the responsible index keys, and validates each revision before updating. A Query Simulator proactively explores demands beyond available queries. Across diverse corpora and retrievers, SELF-INDEX consistently beats existing index optimization methods and extends downstream to search agents and agent memory systems, improving their effectiveness and efficiency.

Related event: SELF-INDEX Enables Self-Evolving Retrieval Indexes for Agents(2 posts)→

Original post →

More from coding & agent

coding & agent channel →