[
    {
        "id": "osp-16005",
        "type": "article-journal",
        "title": "An LLM-in-the-loop RL Framework for Bioinformatics Feature Selection",
        "author": [
            {
                "family": "Wang",
                "given": "Xinyuan"
            },
            {
                "family": "Agrawal",
                "given": "Deepti"
            },
            {
                "family": "Fu",
                "given": "Yanjie"
            }
        ],
        "URL": "https://omanscience.com/en/articles/an-llm-in-the-loop-rl-framework-for-bioinformatics-feature-selection",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "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."
    }
]