mlsanityData to 7 Oct 2026

Self-Evolving Search Index

arXiv 2609.19656 ↗First posted 17 Sep 2026cs.IR cs.AIcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

also in 1 more
Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 30 of its 45 references that are in the map. First posted on arXiv 17 Sep 2026.

Builds on

30 of 45 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction3 May
  2. 2026Dr. Zero: Self-Evolving Search Agents without Training Data11 Jan
  3. 2025BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent8 Aug

Other references · 27

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  3. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
  4. 2021Deduplicating Training Data Makes Language Models Bettercited by 705
  5. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 556
  6. 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Datacited by 323
  7. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 253
  8. 2019Document Expansion by Query Predictioncited by 225
  9. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
  10. 2025R-Zero: Self-Evolving Reasoning LLM from Zero Datacited by 210
  11. 2024BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrievalcited by 153
  12. 2023Dense X Retrieval: What Retrieval Granularity Should We Use?cited by 88
15 more
  1. 2025SPICE: Self-Play In Corpus Environments Improves Reasoningcited by 78
  2. 2025ReasonIR: Training Retrievers for Reasoning Taskscited by 76
  3. 2024Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrievalcited by 50
  4. 2024BEAVER: An Enterprise Benchmark for Text-to-SQLcited by 37
  5. 2026Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Datacited by 31
  6. 2023When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasetscited by 25
  7. 2021Keyphrase Generation for Scientific Document Retrievalcited by 23
  8. 2023Doc2Query--: When Less is Morecited by 20
  9. 2024Contextual Document Embeddingscited by 19
  10. 2026LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleaguescited by 17
  11. 2025EnrichIndex: Using LLMs to Enrich Retrieval Indices Offlinecited by 15
  12. 2026Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User Historycited by 14
  13. 2025Imagine All The Relevance: Scenario-Profiled Indexing with Knowledge Expansion for Dense Retrievalcited by 5
  14. 2026RL-Index: Reinforcement Learning for Retrieval Index Reasoningcited by 2
  15. 2026Group-Aware Adaptive Retrieval for Evidence Navigationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
  2. 2025EvolveSearch: An Iterative Self-Evolving Search Agent
  3. 2026RAG without Forgetting: Continual Query-Infused Key Memory
  4. 2026SE-Search: Self-Evolving Search Agent via Memory and Dense Reward
  5. 2026Towards Recursive Self-Evolving Agentic Literature Retrieval
  6. 2026Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki
  7. 2026SelfSearch: Reward-Free Search for Self-Improving Agents
  8. 2026ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval