Author

Yuheng Huang

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Aug 2026

Sleep Disturbance in Adults with Type 2 Diabetes: Psychosocial Factors Across Anxiety Symptom Groups

Purpose Sleep disturbance is common in adults with type 2 diabetes mellitus (T2DM), but associated psychosocial factors may vary by anxiety symptom status. We examined the prevalence of sleep disturbance and associated factors among adults with T2DM in Hainan Province, China. Patients and Methods This multicenter cross-sectional study included 1200 adults with clinician-confirmed T2DM recruited from endocrinology departments of eight tertiary hospitals. Anxiety symptoms were defined as Generalized Anxiety Disorder-7 score ≥5, and sleep disturbance as Athens Insomnia Scale score ≥6. Multivariable logistic regression models were fitted separately for participants with and without anxiety symptoms. Secondary and sensitivity analyses examined continuous sleep scores, a higher anxiety threshold, and overlap from sleep-related questionnaire items. Results Of 1200 participants, 309 had anxiety symptoms and 891 did not. Sleep disturbance affected 631 participants (52.6%) and was more prevalent among those with anxiety symptoms than among those without (82.2% vs 42.3%). In the anxiety-symptom subgroup, higher Patient Health Questionnaire-9, Beck Hopelessness Scale, and post-traumatic stress symptom scores were associated with greater odds of sleep disturbance. In the subgroup without anxiety symptoms, higher Patient Health Questionnaire-9 and Perceived Deficits Questionnaire scores and higher educational level were associated with sleep disturbance. Conclusion Sleep disturbance was common, particularly among participants with anxiety symptoms. Anxiety-stratified analyses identified different exploratory patterns of associated factors. These cross-sectional findings may support more focused sleep and psychosocial assessment but do not establish causal relationships, validated clinical subtypes, or treatment recommendations.

Dexia Li, Wei Jin, Leweihua Lin et al. · Diabetes, Metabolic Syndrome... · 0 citations

#artificial intelligence Preprint Aug 2026

AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing

Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs), yet existing RAG systems often struggle with complex, multi-step reasoning that requires adaptive retrieval and continuous revision of intermediate contexts. Recent reinforcement learning (RL)-based agentic RAG methods partially alleviate this issue, but typically rely on coarse-grained action spaces and trajectory-level rewards, resulting in weak reward assignment and a bias toward short-horizon, stereotyped reasoning template. To address, we propose AgenticRag-R1, a RL framework that deeply integrates reasoning, retrieval, and memory via a memory stack and fine-grained action space, supported by hierarchical action-aware rewards and an information-aware trajectory rejection strategy to enable effective long-horizon learning. Experiments across a diverse set of multi-hop, open-domain, and agentic reasoning benchmarks, spanning multiple backbone model sizes, demonstrate that AgenticRag-R1 consistently outperforms strong baselines. Moreover, AgenticRag-R1 learns more robust, interpretable, and memory-aware reasoning behaviors, highlighting the effect of fine-grained action modeling and information-aware optimization for long-horizon reasoning. Our code is anonymous available at https://github.com/jiangxinke/Harness-RL/tree/AgenticRAG-R1-Whitebox.

Xinke Jiang, Yue Fang, Zhibang Yang et al. · 1 citation