# Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety

arXiv: https://arxiv.org/abs/2506.12482 · HTML: https://mlsanity.com/paper/2506.12482/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 81 of its 118 references that are in the map.
- First posted on arXiv 14 Jun 2025.

## 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, 30 of 81)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [Scalable agent alignment via reward modeling: a research direction](https://mlsanity.com/paper/1811.07871/) (2018)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents](https://mlsanity.com/paper/2302.01560/) (2023)
- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?](https://mlsanity.com/paper/2403.07718/) (2024)
- [Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine](https://mlsanity.com/paper/2311.16452/) (2023)
- [MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning](https://mlsanity.com/paper/2311.10537/) (2023)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [Unsolved Problems in ML Safety](https://mlsanity.com/paper/2109.13916/) (2021)

## Built on by (most cited first, 8 of 8)

- [Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning](https://mlsanity.com/paper/2511.07784/) (2025)
- [LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios](https://mlsanity.com/paper/2508.17692/) (2025)
- [Sovereign Agentic Loops: Decoupling AI Reasoning from Execution in Real-World Systems](https://mlsanity.com/paper/2604.22136/) (2026)
- [MedCTA: A Benchmark for Clinical Tool Agents](https://mlsanity.com/paper/2606.11702/) (2026)
- [From Black-Box Confidence to Measurable Trust in Clinical AI: A Framework for Evidence, Supervision, and Staged Autonomy](https://mlsanity.com/paper/2604.26671/) (2026)
- [TRACE: A Metrologically-Grounded Engineering Framework for Trustworthy Agentic AI Systems in Operationally Critical Domains](https://mlsanity.com/paper/2605.03838/) (2026)
- [The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents](https://mlsanity.com/paper/2608.06663/) (2026)
- [Trust Is Not a Score: Runtime Assurance Contracts for High-Risk AI Agents](https://mlsanity.com/paper/2609.39717/) (2026)

## Abstract (arXiv)

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/