mlsanityData to 14 Oct 2026

Comprehend, Divide, and Conquer: Feature Subspace Exploration via Multi-Agent Hierarchical Reinforcement Learning

arXiv 2504.17356 ↗First posted 24 Apr 2025cs.AI cs.LGcited by 1

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

Abstract (arXiv)

Feature selection aims to preprocess the target dataset, find an optimal and most streamlined feature subset, and enhance the downstream machine learning task. Among filter, wrapper, and embedded-based approaches, the reinforcement learning (RL)-based subspace exploration strategy provides a novel objective optimization-directed perspective and promising performance. Nevertheless, even with improved performance, current reinforcement learning approaches face challenges similar to conventional methods when dealing with complex datasets. These challenges stem from the inefficient paradigm of using one agent per feature and the inherent complexities present in the datasets. This observation motivates us to investigate and address the above issue and propose a novel approach, namely HRLFS. Our methodology initially employs a Large Language Model (LLM)-based hybrid state extractor to capture each feature's mathematical and semantic characteristics. Based on this information, features are clustered, facilitating the construction of hierarchical agents for each cluster and sub-cluster. Extensive experiments demonstrate the efficiency, scalability, and robustness of our approach. Compared to contemporary or the one-feature-one-agent RL-based approaches, HRLFS improves the downstream ML performance with iterative feature subspace exploration while accelerating total run time by reducing the number of agents involved.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 28 of its 79 references that are in the map. First posted on arXiv 24 Apr 2025.

Builds on

28 of 79 references.

References · 28

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
  3. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  4. 2015Prioritized Experience Replaycited by 1,099
  5. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 785
  6. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  7. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 567
  8. 2020A Finite Time Analysis of Two Time-Scale Actor Critic Methodscited by 122
  9. 2016Feature Selection: A Data Perspectivecited by 50
  10. 2019Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discoverycited by 43
  11. 2018DeepPINK: reproducible feature selection in deep neural networkscited by 41
  12. 2022Group-wise Reinforcement Feature Generation for Optimal and Explainable Representation Space Reconstructioncited by 35
16 more
  1. 2023Beyond Discrete Selection: Continuous Embedding Space Optimization for Generative Feature Selectioncited by 28
  2. 2020Consistent Feature Selection for Analytic Deep Neural Networkscited by 27
  3. 2024Exploring Large Language Models for Feature Selection: A Data-centric Perspectivecited by 27
  4. 2022Traceable Automatic Feature Transformation via Cascading Actor-Critic Agentscited by 26
  5. 2020AutoFS: Automated Feature Selection via Diversity-aware Interactive Reinforcement Learningcited by 24
  6. 2023Traceable Group-Wise Self-Optimizing Feature Transformation Learning: A Dual Optimization Perspectivecited by 24
  7. 2023A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learningcited by 24
  8. 2017Kernel Feature Selection via Conditional Covariance Minimizationcited by 20
  9. 2021Efficient Reinforced Feature Selection via Early Stopping Traverse Strategycited by 19
  10. 2019Option-Critic in Cooperative Multi-agent Systemscited by 17
  11. 2022Composite Feature Selection using Deep Ensemblescited by 11
  12. 2024Revolutionizing Biomarker Discovery: Leveraging Generative AI for Bio-Knowledge-Embedded Continuous Space Explorationcited by 11
  13. 2023A Partially Supervised Reinforcement Learning Framework for Visual Active Searchcited by 8
  14. 2025Knowledge Hierarchy Guided Biological-Medical Dataset Distillation for Domain LLM Trainingcited by 5
  15. 2025FastFT: Accelerating Reinforced Feature Transformation via Advanced Exploration Strategiescited by 5
  16. 2024Causal Feature Selection for Responsible Machine Learningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026SciHorizon-GENE: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Functional Understandingcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Automation and Feature Selection Enhancement with Reinforcement Learning (RL)
  2. 2025Discovering Temporal Structure: An Overview of Hierarchical Reinforcement Learning
  3. 2026Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic Search
  4. 2024Boosting Hierarchical Reinforcement Learning with Meta-Learning for Complex Task Adaptation
  5. 2025A Multi-Component Reward Function with Policy Gradient for Automated Feature Selection with Dynamic Regularization and Bias Mitigation
  6. 2025Dual-Agent Reinforcement Learning for Automated Feature Generation
  7. 2025Toward Efficient Exploration by Large Language Model Agents
  8. 2025Heterogeneous Multi-Agent Reinforcement Learning with Attention for Cooperative and Scalable Feature Transformation