# An LLM-in-the-loop RL Framework for Bioinformatics Feature Selection

arXiv: https://arxiv.org/abs/2610.05600 · HTML: https://mlsanity.com/paper/2610.05600/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 15 references that are in the map.
- First posted on arXiv 4 Oct 2026.

## Builds on (most cited first, 4 of 4)

- [Simplifying Reinforced Feature Selection via Restructured Choice Strategy of Single Agent](https://mlsanity.com/paper/2009.09230/) (2020)
- [Knockoff-Guided Feature Selection via A Single Pre-trained Reinforced Agent](https://mlsanity.com/paper/2403.04015/) (2024)
- [Neuro-Symbolic Embedding for Short and Effective Feature Selection via Autoregressive Generation](https://mlsanity.com/paper/2404.17157/) (2024)
- [Feature Selection Using Reinforcement Learning](https://mlsanity.com/paper/2101.09460/) (2021)

## Abstract (arXiv)

High-dimensional bioinformatics data, characterized by a large number of features relative to the number of samples, pose major challenges such as the ``curse of dimensionality,'' leading to overfitting, high computational cost, and poor generalization. Traditional feature selection methods often suffer from limited scalability and adaptability in such domains. We propose an LLM-in-the-loop reinforcement learning (RL) framework for bioinformatics feature selection, where the RL agent formulates feature selection as a sequential decision-making task, while the large language model (LLM) enhances the process in two ways: (1) guiding exploration through domain-informed advice, and (2) providing hybrid rewards that integrate data-driven performance with knowledge-driven evaluation. The LLM also produces explanations to improve interpretability for human experts without altering the RL policy update. Experiments on diverse bioinformatics datasets show that the LLM-in-the-loop framework outperforms baselines, achieves stable performance across downstream models, and converges faster than pure RL.