mlsanityData to 14 Oct 2026

A New Paradigm in Tuning Learned Indexes: A Reinforcement Learning Enhanced Approach

arXiv 2502.05001 ↗First posted 7 Feb 2025cs.DB cs.AI cs.SYcited by 2

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

Learned Index Structures (LIS) have significantly advanced data management by leveraging machine learning models to optimize data indexing. However, designing these structures often involves critical trade-offs, making it challenging for both designers and end-users to find an optimal balance tailored to specific workloads and scenarios. While some indexes offer adjustable parameters that demand intensive manual tuning, others rely on fixed configurations based on heuristic auto-tuners or expert knowledge, which may not consistently deliver optimal performance. This paper introduces LITune, a novel framework for end-to-end automatic tuning of Learned Index Structures. LITune employs an adaptive training pipeline equipped with a tailor-made Deep Reinforcement Learning (DRL) approach to ensure stable and efficient tuning. To accommodate long-term dynamics arising from online tuning, we further enhance LITune with an on-the-fly updating mechanism termed the O2 system. These innovations allow LITune to effectively capture state transitions in online tuning scenarios and dynamically adjust to changing data distributions and workloads, marking a significant improvement over other tuning methods. Our experimental results demonstrate that LITune achieves up to a 98% reduction in runtime and a 17-fold increase in throughput compared to default parameter settings given a selected Learned Index instance. These findings highlight LITune's effectiveness and its potential to facilitate broader adoption of LIS in real-world applications.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 22 of its 54 references that are in the map. First posted on arXiv 7 Feb 2025.

Builds on

22 of 54 references.

References · 22

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015Continuous control with deep reinforcement learningcited by 3,407
  3. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 774
  4. 2017Learning Combinatorial Optimization Algorithms over Graphscited by 561
  5. 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 297
  6. 2017The Case for Learned Index Structurescited by 188
  7. 2019Benchmarking Model-Based Reinforcement Learningcited by 162
  8. 2017Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Controlcited by 53
  9. 2019ALEX: An Updatable Adaptive Learned Indexcited by 43
  10. 2020RadixSpline: A Single-Pass Learned Indexcited by 31
  11. 2018FITing-Tree: A Data-aware Index Structurecited by 30
  12. 2019SOSD: A Benchmark for Learned Indexescited by 21
10 more
  1. 2018Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Searchcited by 18
  2. 2019The PGM-index: a multicriteria, compressed and learned approach to data indexingcited by 17
  3. 2021Updatable Learned Index with Precise Positionscited by 13
  4. 2021CARMI: A Cache-Aware Learned Index with a Cost-based Construction Algorithmcited by 8
  5. 2021APEX: A High-Performance Learned Index on Persistent Memorycited by 6
  6. 2023Learning to Optimize LSM-trees: Towards A Reinforcement Learning based Key-Value Store for Dynamic Workloadscited by 6
  7. 2024Accelerating String-Key Learned Index Structures via Memoization-based Incremental Trainingcited by 4
  8. 2021Towards Practical Learned Indexingcited by 3
  9. 2023AirIndex: Versatile Index Tuning Through Data and Storagecited by 3
  10. 2023ML-Powered Index Tuning: An Overview of Recent Progress and Open Challengescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agentscited by 15
  2. 2026Mathematical Foundations of Poisoning Attacks on Linear Regression over Cumulative Distribution Functionscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024UpLIF: An Updatable Self-Tuning Learned Index Framework
  2. 2025AutoIndexer: A Reinforcement Learning-Enhanced Index Advisor Towards Scaling Workloads
  3. 2024IA2: Leveraging Instance-Aware Index Advisor with Reinforcement Learning for Diverse Workloads
  4. 2026RL-Index: Reinforcement Learning for Retrieval Index Reasoning
  5. 2025Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
  6. 2025L2T-Tune:LLM-Guided Hybrid Database Tuning with LHS and TD3
  7. 2025Rethinking On-policy Optimization for Query Augmentation
  8. 2025DemoTuner: Automatic Performance Tuning for Database Management Systems Based on Demonstration Reinforcement Learning