On the possibilities and limitations of LLM-based multi-agent systems for multi-criteria decision-making in healthcare operations management
arXiv cs.AI · 17 Oct 2026, 02:05 AEST
A framework has been proposed to assess the reliability of LLM-generated preferences for multi-criteria decision-making in healthcare operations. The study reveals that explicit preferences vary by role and operating conditions, while implicit preferences are influenced by presentation order.
Key facts
- Multi-criteria models for healthcare operations need weights that express how stakeholders trade off patient waiting time, provider workload, and operating cost, but these weights are difficult to quantify.
- Teams of large language model (LLM) agents, each prompted to represent a stakeholder, have been used to supply them.
- The computational experiments show that the explicit preferences respond to the clinic's operating conditions and differ across roles, but deliberation among the agents can erase these differences, whereas simple averaging preserves them.
- We then formulate robust weighted-sum optimization models to account for preference uncertainty.
- These results indicate that LLM-generated preferences need an audit of this kind before they are used as optimization weights in healthcare decision support.
Read aloud
A framework has been proposed to assess the reliability of L L M-generated preferences for multi-criteria decision-making in healthcare operations. The study reveals that explicit preferences vary by role and operating conditions, while implicit preferences are influenced by presentation order. Multi-criteria models for healthcare operations need weights that express how stakeholders trade off patient waiting time, provider workload, and operating cost, but these weights are difficult to quantify. Teams of large language model L L M agents, each prompted to represent a stakeholder, have been used to supply them. The computational experiments show that the explicit preferences respond to the clinic's operating conditions and differ across roles, but deliberation among the agents can erase these differences, whereas simple averaging preserves them. We then formulate robust weighted-sum optimization models to account for preference uncertainty. These results indicate that L L M-generated preferences need an audit of this kind before they are used as optimization weights in healthcare decision support.
Sources in this cluster
- On the possibilities and limitations of LLM-based multi-agent systems for multi-criteria decision-making in healthcare operations management
arXiv cs.AI · 17 Oct 2026, 02:05 AEST