Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914060206866432 |
|---|---|
| author | Kim, Yubin Jeong, Hyewon Park, Chanwoo Park, Eugene Zhang, Haipeng Liu, Xin Lee, Hyeonhoon McDuff, Daniel Ghassemi, Marzyeh Breazeal, Cynthia Tulebaev, Samir Park, Hae Won |
| author_facet | Kim, Yubin Jeong, Hyewon Park, Chanwoo Park, Eugene Zhang, Haipeng Liu, Xin Lee, Hyeonhoon McDuff, Daniel Ghassemi, Marzyeh Breazeal, Cynthia Tulebaev, Samir Park, Hae Won |
| contents | Large language models (LLMs) deployed as agents introduce significant safety risks in clinical settings due to their potential for error and single points of failure. We introduce Tiered Agentic Oversight (TAO), a hierarchical multi-agent system that enhances AI safety through layered, automated supervision. Inspired by clinical hierarchies (e.g., nurse-physician-specialist) in hospital, TAO routes tasks to specialized agents based on complexity, creating a robust safety framework through automated inter- and intra-tier communication and role-playing. Crucially, this hierarchical structure functions as an effective error-correction mechanism, absorbing up to 24% of individual agent errors before they can compound. Our experiments reveal TAO outperforms single-agent and other multi-agent systems on 4 out of 5 healthcare safety benchmarks, with up to an 8.2% improvement. Ablation studies confirm key design principles of the system: (i) its adaptive architecture is over 3% safer than static, single-tier configurations, and (ii) its lower tiers are indispensable, as their removal causes the most significant degradation in overall safety. Finally, we validated the system's synergy with human doctors in a user study where a physician, acting as the highest tier agent, provided corrective feedback that improved medical triage accuracy from 40% to 60%. Project Page: https://tiered-agentic-oversight.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_12482 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety Kim, Yubin Jeong, Hyewon Park, Chanwoo Park, Eugene Zhang, Haipeng Liu, Xin Lee, Hyeonhoon McDuff, Daniel Ghassemi, Marzyeh Breazeal, Cynthia Tulebaev, Samir Park, Hae Won Artificial Intelligence Large language models (LLMs) deployed as agents introduce significant safety risks in clinical settings due to their potential for error and single points of failure. We introduce Tiered Agentic Oversight (TAO), a hierarchical multi-agent system that enhances AI safety through layered, automated supervision. Inspired by clinical hierarchies (e.g., nurse-physician-specialist) in hospital, TAO routes tasks to specialized agents based on complexity, creating a robust safety framework through automated inter- and intra-tier communication and role-playing. Crucially, this hierarchical structure functions as an effective error-correction mechanism, absorbing up to 24% of individual agent errors before they can compound. Our experiments reveal TAO outperforms single-agent and other multi-agent systems on 4 out of 5 healthcare safety benchmarks, with up to an 8.2% improvement. Ablation studies confirm key design principles of the system: (i) its adaptive architecture is over 3% safer than static, single-tier configurations, and (ii) its lower tiers are indispensable, as their removal causes the most significant degradation in overall safety. Finally, we validated the system's synergy with human doctors in a user study where a physician, acting as the highest tier agent, provided corrective feedback that improved medical triage accuracy from 40% to 60%. Project Page: https://tiered-agentic-oversight.github.io/ |
| title | Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2506.12482 |