Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.10461 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911205777473536 |
|---|---|
| author | Zheng, Hongjie Shi, Zesheng Yi, Ping |
| author_facet | Zheng, Hongjie Shi, Zesheng Yi, Ping |
| contents | Autonomous agents utilizing Large Language Models (LLMs) have demonstrated remarkable capabilities in isolated medical tasks like diagnosis and image analysis, but struggle with integrated clinical workflows that connect diagnostic reasoning and medication decisions. We identify a core limitation: existing medical AI systems process tasks in isolation without the cross-validation and knowledge integration found in clinical teams, reducing their effectiveness in real-world healthcare scenarios. To transform the isolation paradigm into a collaborative approach, we propose MedCoAct, a confidence-aware multi-agent framework that simulates clinical collaboration by integrating specialized doctor and pharmacist agents, and present a benchmark, DrugCareQA, to evaluate medical AI capabilities in integrated diagnosis and treatment workflows. Our results demonstrate that MedCoAct achieves 67.58\% diagnostic accuracy and 67.58\% medication recommendation accuracy, outperforming single agent framework by 7.04\% and 7.08\% respectively. This collaborative approach generalizes well across diverse medical domains, proving especially effective for telemedicine consultations and routine clinical scenarios, while providing interpretable decision-making pathways. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10461 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MedCoAct: Confidence-Aware Multi-Agent Collaboration for Complete Clinical Decision Zheng, Hongjie Shi, Zesheng Yi, Ping Artificial Intelligence Autonomous agents utilizing Large Language Models (LLMs) have demonstrated remarkable capabilities in isolated medical tasks like diagnosis and image analysis, but struggle with integrated clinical workflows that connect diagnostic reasoning and medication decisions. We identify a core limitation: existing medical AI systems process tasks in isolation without the cross-validation and knowledge integration found in clinical teams, reducing their effectiveness in real-world healthcare scenarios. To transform the isolation paradigm into a collaborative approach, we propose MedCoAct, a confidence-aware multi-agent framework that simulates clinical collaboration by integrating specialized doctor and pharmacist agents, and present a benchmark, DrugCareQA, to evaluate medical AI capabilities in integrated diagnosis and treatment workflows. Our results demonstrate that MedCoAct achieves 67.58\% diagnostic accuracy and 67.58\% medication recommendation accuracy, outperforming single agent framework by 7.04\% and 7.08\% respectively. This collaborative approach generalizes well across diverse medical domains, proving especially effective for telemedicine consultations and routine clinical scenarios, while providing interpretable decision-making pathways. |
| title | MedCoAct: Confidence-Aware Multi-Agent Collaboration for Complete Clinical Decision |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.10461 |