Self-Evolving Search Index
SELF-INDEX enables a search index to autonomously diagnose retrieval failures and revise its keys, improving LLM agent retrieval and memory.
The paper proposes SELF-INDEX, a framework in which a retrieval index self-evolves without human intervention. An Optimizer diagnoses retrieval shortfalls, selectively revises the responsible index keys, and validates each revision before updating, while a Query Simulator proactively explores demands beyond observed queries. Across diverse corpora and retrievers, SELF-INDEX consistently improves retrieval performance, outperforming existing index optimization methods and benefiting downstream search agents and agent memory systems.
- Optimizer autonomously diagnoses and revises faulty index keys with validation
- Query Simulator explores retrieval demands beyond observed queries
- Outperforms existing index optimization across diverse corpora and retrievers
- Improves downstream search agents and agent memory retrieval
Full article193 words · extracted from huggingface.co · click to collapse
Information retrieval is increasingly important as LLM agents tackle complex tasks involving diverse information needs. Because retrieval relies on an index that represents each document through index keys, retrieval quality depends heavily on how effectively these keys expose the knowledge contained in each document. However, effective index representations vary across retrieval environments, making it difficult for any fixed optimization strategy to perform consistently. Yet evolving an index to its retrieval environment remains largely human-driven, requiring humans to diagnose retrieval failures, refine the optimization strategy, and reprocess the index accordingly. We propose SELF-INDEX, a framework that enables an index to self-evolve without human intervention. Its Optimizer autonomously diagnoses retrieval shortfalls, selectively revises the responsible index keys, and validates each revision before updating the index. Beyond reacting to observed retrieval demands, SELF-INDEX proactively explores additional demands through a Query Simulator, allowing the index to evolve beyond the queries already available for optimization. Across diverse corpora and retrievers, SELF-INDEX consistently improves retrieval performance while outperforming existing index optimization methods. We further show that these benefits extend to downstream applications, improving the effectiveness and efficiency of search agents and helping agent memory systems retrieve useful past interactions.
Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/papers/2609.19656