Tairex Launches Multi-Agent AI System to Transform Clinical Collaboration and Decision Support

On October 21, 2026, Tairex, an AI healthcare technology company incubated by the Institute for AI Industry Research (AIR) at Tsinghua University, unveiled the Multidisciplinary Human-Agent Collaboration (MHAC) Ecosystem for Agent Hospital, designed to enable specialized AI agents to work alongside physicians on clinical cases.

While AI systems have become increasingly capable of addressing individual clinical tasks, coordinating their outputs around the same patient remains a challenge. Tairex’s approach is to move beyond standalone AI tools by developing an ecosystem of specialized agents that can work together within clinical workflows. Rather than building a single, all-purpose AI doctor, the company aims to enable AI systems to support physicians through coordinated, cross-specialty collaboration.

From Virtual Training to Real-World Collaboration

In a simulated environment populated by millions of highly realistic AI patients, an AI doctor can conduct tens of thousands of simulated consultations daily. These synthetic patients are partially generated based on clinical guidelines and medical literature rather than simply reproducing real medical records, helping mitigate patient privacy risks.

This intensive virtual training yields a system comprising 54 AI doctors and millions of AI patients, covering more than 20 clinical specialties and tens of thousands of diseases. The AI doctors have achieved over 96% accuracy on the MedQA dataset.

The system can learn from clinical feedback, adapting to doctors’ consultation styles and diagnostic reasoning. 

The core capability of the newly launched Tairex Multidisciplinary Human-Agent Collaboration Ecosystem lies in its ability to organize specialized doctor avatar agents into a coordinated virtual team.

When a patient’s condition spans multiple specialties, the system dynamically activates relevant agents to work simultaneously. Rather than operating in silos, these agents present their clinical reasoning and evidence on a unified interface, with disagreements highlighted for the human physician’s review.

When an endocrinology agent proposed a beta-blocker for a patient with palpitations and a history of asthma, a respiratory medicine agent flagged that non-selective beta-blockers could trigger bronchoconstriction and suggested considering a selective beta-1 blocker.

The case illustrates how collaboration among specialized AI agents can help doctors identify risks that may be overlooked from a single-specialty perspective.

Reshaping Clinical Workflows Through AI Collaboration

Multidisciplinary team (MDT) consultations are increasingly important for complex diseases, but their implementation can be hindered by scheduling conflicts, gaps between recommendations and treatment execution, and fragmented patient journeys across departments.

Tairex’s MHAC Ecosystem addresses these challenges by bringing multidisciplinary input into the initial consultation. Specialized AI agents can provide simultaneous recommendations within the clinical interface, allowing doctors to consider cross-specialty perspectives without waiting for a separate meeting.

The system can also extend access to specialist expertise by enabling AI agents modeled on specialists to support multiple departments and potentially reach primary care facilities, helping make high-quality medical resources more widely accessible.

Under this model, AI is designed to improve efficiency and support clinical decision-making rather than independently make critical decisions.

Ultimately, the value of AI healthcare should be measured by tangible improvements in doctors’ time, quality of care, patient experience and access to primary care. A measurable and trustworthy ecosystem is essential for AI to become an effective clinical partner.

Data security is also built into the system’s design. Tairex’s underlying products take reference from the EU’s General Data Protection Regulation (GDPR) and South Korea’s Personal Information Protection Act (PIPA), with controls governing the handling and transfer of sensitive data fields. The company has also obtained China’s Multi-Level Protection Scheme (MLPS) Level 3 certification.

By integrating AI-assisted workflows with human-led clinical decision-making, Tairex’s Multidisciplinary Human-Agent Collaboration Ecosystem aims to help high-quality medical resources reach more healthcare institutions, including those at the primary care level, bringing more equitable access to healthcare closer to reality.