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

• URL: http://arxiv.org/abs/2506.12482v2
• Date: Sun, 28 Sep 2025 22:10:16 GMT
• Title: Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety
• Authors: Yubin Kim, Hyewon Jeong, Chanwoo Park, Eugene Park, Haipeng Zhang, Xin Liu, Hyeonhoon Lee, Daniel McDuff, Marzyeh Ghassemi, Cynthia Breazeal, Samir Tulebaev, Hae Won Park,
• Abstract summary: Tiered Agentic Oversight (TAO) is a hierarchical multi-agent system that enhances AI safety through layered, automated supervision.<n>Inspired by clinical hierarchies (e.g., nurse-physician-specialist) in hospital, TAO routes tasks to specialized agents based on complexity.<n>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.
• Score: 39.9193491638205
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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/

Related papers

• AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security [126.49733412191416]
  Current guardrail models lack agentic risk awareness and transparency in risk diagnosis.<n>We propose a unified three-dimensional taxonomy that categorizes agentic risks by their source (where), failure mode (how), and consequence (what)<n>We introduce a new fine-grained agentic safety benchmark (ATBench) and a Diagnostic Guardrail framework for agent safety and security (AgentDoG)
  arXiv  Detail & Related papers  (2026-01-26T13:45:41Z)
• INFA-Guard: Mitigating Malicious Propagation via Infection-Aware Safeguarding in LLM-Based Multi-Agent Systems [70.37731999972785]
  In this paper, we propose Infection-Aware Guard, INFA-Guard, a novel defense framework that explicitly identifies and addresses infected agents as a distinct threat category.<n>During remediation, INFA-Guard replaces attackers and rehabilitates infected ones, avoiding malicious propagation while preserving topological integrity.
  arXiv  Detail & Related papers  (2026-01-21T05:27:08Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning [49.31650627835956]
  Partial agent failure becomes inevitable when systems scale up, making it crucial to identify the subset of agents whose compromise would most severely degrade overall performance.<n>In this paper, we study this Vulnerable Agent Identification (VAI) problem in large-scale multi-agent reinforcement learning (MARL)<n> Experiments show our method effectively identifies more vulnerable agents in large-scale MARL and the rule-based system, fooling system into worse failures, and learning a value function that reveals the vulnerability of each agent.
  arXiv  Detail & Related papers  (2025-09-18T16:03:50Z)
• Collaborative Medical Triage under Uncertainty: A Multi-Agent Dynamic Matching Approach [4.474709234869498]
  Post-pandemic surge in healthcare demand, coupled with critical nursing shortages, has placed unprecedented pressure on medical triage systems.<n>We present a multi-agent interactive intelligent system for medical triage that addresses three fundamental challenges in current AI-based triage systems.
  arXiv  Detail & Related papers  (2025-07-30T09:21:59Z)
• WebGuard: Building a Generalizable Guardrail for Web Agents [59.31116061613742]
  WebGuard is the first dataset designed to support the assessment of web agent action risks.<n>It contains 4,939 human-annotated actions from 193 websites across 22 diverse domains.
  arXiv  Detail & Related papers  (2025-07-18T18:06:27Z)
• OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety [58.201189860217724]
  We introduce OpenAgentSafety, a comprehensive framework for evaluating agent behavior across eight critical risk categories.<n>Unlike prior work, our framework evaluates agents that interact with real tools, including web browsers, code execution environments, file systems, bash shells, and messaging platforms.<n>It combines rule-based analysis with LLM-as-judge assessments to detect both overt and subtle unsafe behaviors.
  arXiv  Detail & Related papers  (2025-07-08T16:18:54Z)
• MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systems [24.60202452646343]
  We introduce MedSentry, a benchmark 5 000 adversarial medical prompts spanning 25 categories with 100 subthemes.<n>We develop an end-to-end attack-defense evaluation pipeline to analyze how four representative multi-agent topologies withstand attacks from 'dark-personality' agents.
  arXiv  Detail & Related papers  (2025-05-27T07:34:40Z)
• ALRPHFS: Adversarially Learned Risk Patterns with Hierarchical Fast \& Slow Reasoning for Robust Agent Defense [7.923638619678924]
  Existing defenses rely on "Safety Checks", which struggle to capture the complex semantic risks posed by harmful user inputs or unsafe agent behaviors.<n>We propose a novel defense framework, ALRPHFS (Adversarially Learned Risk Patterns with Hierarchical Fast & Slow Reasoning)<n>ALRPHFS consists of two core components: (1) an offline adversarial self-learning loop to iteratively refine a generalizable and balanced library of risk patterns, and (2) an online hierarchical fast & slow reasoning engine that balances detection effectiveness with computational efficiency.
  arXiv  Detail & Related papers  (2025-05-25T18:31:48Z)
• PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning [8.191214701984162]
  Multi-agent systems leverage advanced AI models as autonomous agents that interact, cooperate, or compete to complete complex tasks.<n>Despite their growing importance, safety in multi-agent systems remains largely underexplored.<n>This work investigates backdoor vulnerabilities in multi-agent systems and proposes a defense mechanism based on agent interactions.
  arXiv  Detail & Related papers  (2025-05-16T19:08:29Z)
• Toward Automated Regulatory Decision-Making: Trustworthy Medical Device Risk Classification with Multimodal Transformers and Self-Training [3.439579933384111]
  Transformer-based framework integrates textual descriptions and visual information to predict device regulatory classification.<n>Our approach achieves up to 90.4% accuracy and 97.9% AUROC, significantly outperforming text-only (77.2%) and image-only (54.8%) baselines.
  arXiv  Detail & Related papers  (2025-05-01T09:41:41Z)
• AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security [74.22452069013289]
  AegisLLM is a cooperative multi-agent defense against adversarial attacks and information leakage.<n>We show that scaling agentic reasoning system at test-time substantially enhances robustness without compromising model utility.<n> Comprehensive evaluations across key threat scenarios, including unlearning and jailbreaking, demonstrate the effectiveness of AegisLLM.
  arXiv  Detail & Related papers  (2025-04-29T17:36:05Z)
• D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security [22.86304661035188]
  D-CIPHER is a multi-agent framework for collaborative cybersecurity CTF solving.<n>It integrates agents with distinct roles with dynamic feedback loops to enhance reasoning on complex tasks.<n>It achieves state-of-the-art performance on three benchmarks: 22.0% on NYU CTF Bench, 22.5% on Cybench, and 44.0% on HackTheBox.
  arXiv  Detail & Related papers  (2025-02-15T23:43:18Z)
• Agent-SafetyBench: Evaluating the Safety of LLM Agents [72.92604341646691]
  We introduce Agent-SafetyBench, a benchmark designed to evaluate the safety of large language models (LLMs)<n>Agent-SafetyBench encompasses 349 interaction environments and 2,000 test cases, evaluating 8 categories of safety risks and covering 10 common failure modes frequently encountered in unsafe interactions.<n>Our evaluation of 16 popular LLM agents reveals a concerning result: none of the agents achieves a safety score above 60%.
  arXiv  Detail & Related papers  (2024-12-19T02:35:15Z)
• On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents [58.79302663733703]
  Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents.<n>The impact of clumsy or even malicious agents--those who frequently make errors in their tasks--on the overall performance of the system remains underexplored.<n>This paper investigates what is the resilience of various system structures under faulty agents on different downstream tasks.
  arXiv  Detail & Related papers  (2024-08-02T03:25:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.