# Human-in-the-Loop Multi-Agent Ventilator Decision Support with Contextual Bandit Preference Learning

arXiv: https://arxiv.org/abs/2605.23320 · HTML: https://mlsanity.com/paper/2605.23320/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 4 of its 27 references that are in the map.
- First posted on arXiv 22 May 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

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

- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [An Actor-Critic Contextual Bandit Algorithm for Personalized Mobile Health Interventions](https://mlsanity.com/paper/1706.09090/) (2017)
- [Contract-based Design and Verification of Multi-Agent Systems with Quantitative Temporal Requirements](https://mlsanity.com/paper/2412.13114/) (2024)

## Abstract (arXiv)

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.