{"slug": "human-in-the-loop-multi-agent-ventilator-decision-support-with-contextual-bandit", "title": "Human-in-the-Loop Multi-Agent Ventilator Decision Support with Contextual Bandit Preference Learning", "summary": "Researchers have developed the Ventilator Decision Support System (VDSS), a human-in-the-loop multi-agent framework that coordinates modular decision components through structured interfaces to provide traceable, personalized ventilator recommendations. The system uses a contextual bandit to adapt to clinician-specific preferences from accepted decisions and incorporates structured rejection feedback to reduce unproductive iterations. Retrospective ICU trajectory replay with expert review showed higher recommendation acceptability and fewer interaction rounds, supporting clinically deployable human-AI collaboration.", "body_md": "arXiv:2605.23320v1 Announce Type: new\nAbstract: Ventilator decision support requires sequential decisions that track evolving physiology and disease trajectories while respecting safety boundaries and clinician specific tuning styles. Rule based approaches rarely generalize personalization, and end to end reinforcement learning or single large language model systems remain difficult to control and audit. We propose the Ventilator Decision Support System (VDSS), a human in the loop multi agent framework that coordinates modular decision components through contract driven structured interfaces and produces traceable evidence for review. VDSS performs online preference adaptation with a contextual bandit, updating clinician specific preferences from the final accepted decision at each adjustment cycle and using them to guide subsequent recommendations. Structured rejection feedback triggers targeted replanning to reduce unproductive iterations and improve interaction stability. Retrospective ICU trajectory replay with expert review indicates higher recommendation acceptability and fewer interaction rounds to reach an acceptable plan, supporting clinically deployable human AI collaboration.", "url": "https://wpnews.pro/news/human-in-the-loop-multi-agent-ventilator-decision-support-with-contextual-bandit", "canonical_source": "https://arxiv.org/abs/2605.23320", "published_at": "2026-05-25 04:00:00+00:00", "updated_at": "2026-05-25 15:17:33.147118+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-agents", "ai-safety", "ai-research"], "entities": ["Ventilator Decision Support System", "VDSS"], "alternates": {"html": "https://wpnews.pro/news/human-in-the-loop-multi-agent-ventilator-decision-support-with-contextual-bandit", "markdown": "https://wpnews.pro/news/human-in-the-loop-multi-agent-ventilator-decision-support-with-contextual-bandit.md", "text": "https://wpnews.pro/news/human-in-the-loop-multi-agent-ventilator-decision-support-with-contextual-bandit.txt", "jsonld": "https://wpnews.pro/news/human-in-the-loop-multi-agent-ventilator-decision-support-with-contextual-bandit.jsonld"}}