CRC-Router: Risk-Constrained Routing for Medical Agentic AI Systems

Xueyang Li; Mingze Jiang; Gelei Xu; Jun Xia; Ching-Hao Chiu; Mengzhao Jia; Danny Z. Chen; Yiyu Shi

cs.AISep 25, 2026

CRC-Router: Risk-Constrained Routing for Medical Agentic AI Systems

Authors: Xueyang Li, Mingze Jiang, Gelei Xu, Jun Xia, Ching-Hao Chiu, Mengzhao Jia, Danny Z. Chen, Yiyu Shi

Organizations: Computer Science and Engineering, University of Notre Dame, USA

Abstract

Agentic AI systems are increasingly being explored in medical imaging to improve throughput and reduce clinician workload; however, safe deployment remains challenging because autonomous errors may propagate into downstream clinical decisions. A central requirement is therefore not only strong predictive performance, but also a reliable routing mechanism that determines when the system should proceed autonomously and when a case should be escalated for further review. To address this gap, we propose CRC-Router, a risk-constrained, uncertainty-aware routing module that is applicable to both conventional medical prediction models and agentic medical AI systems. CRC-Router combines multiple complementary uncertainty signals with the predictive score to construct a per-finding routing feature vector, maps this vector to an estimated wrong-accept risk using a lightweight per-finding risk model, and then applies Conformal Risk Control (CRC) to calibrate acceptance thresholds under a user-specified risk target. Instantiated on chest X-ray multi-finding triage using the NIH ChestX-ray14 dataset, CRC-Router achieves the strongest empirical risk--coverage trade-off among the evaluated baselines, both as a standalone routing layer and as a plug-in module integrated with the state-of-the-art MedRAX agent. These results demonstrate both the effectiveness of CRC-Router in selective medical automation and its modular, model-agnostic compatibility with existing predictive and agentic medical pipelines. Code is publicly available at https://github.com/XLIAaron/CRC-Router

Figures & tables

Fig. 1: Overview of the proposed CRC-Router. (a) Multi-signal uncertainty and risk modeling. (b) Conformal Risk Control (CRC)-based threshold calibration and deployment routing.

Disease	Accept -All	MaxProb [ 20 ]	MCD-MI [ 21 ]	Conformal Pred. [ 19 ]	CRC-Router	Risk Red. $\dagger$
Atelectasis	17.0%	5.4%	10.6%	11.9%	3.9%✓	$\downarrow$ 77%
Cardiomegaly	3.8%✓	1.5%✓	1.3%✓	1.1%✓	3.8%✓	–
Consolidation	18.1%	9.8%	17.8%	9.6%	4.4%✓	$\downarrow$ 76%
Edema	2.8%✓	0.8%✓	0.8%✓	1.0%✓	2.8%✓	–
Effusion	14.8%	5.1%	9.3%	9.6%	4.4%✓	$\downarrow$ 70%
Emphysema	2.3%✓	1.4%✓	0.8%✓	0.9%✓	2.3%✓	–

TABLE I: Per-disease risk (

\hat{R}_{d}

) across routing methods (

\alpha=5\%

). All selective methods are matched to

{\sim}

91% macro coverage. Best results among selective methods are highlighted in bold. ✓ indicates

\hat{R}_{d}\leq\alpha

\dagger

Relative reduction of CRC-Router risk compared to Accept-All; “–” indicates the Accept-All risk is already below

\alpha

NIH ChestX-ray14 [ 22 ]				CheXpert [ 23 ]
Disease	MedRAX [ 10 ]	+CR * (TTA)	+CR * (MoE)	Disease	MedRAX [ 10 ]	+CR * (TTA)
Atelectasis	6.6%	4.7%✓	4.0%✓	Enl. Cardiomed.	57.6%	4.2%✓
Cardiomegaly	12.9%	3.6%✓	3.7%✓	Cardiomegaly	51.3%	4.7%✓
Consolidation	9.6%	6.6%	3.4%✓	Lung Opacity	30.1%	4.7%✓
Edema	6.5%	6.2%	2.9%✓	Lung Lesion	1.5%✓	3.9%✓
Effusion	14.5%	5.9%	4.3%✓	Edema	19.4%	4.3%✓

TABLE II: Per-disease wrong-accept risk (

\hat{R}_{d}

) for MedRAX integration at

\alpha=5\%

on NIH ChestX-ray14 and CheXpert. CR * =CRC-Router. MoE is omitted on CheXpert as the committee was not trained on CheXpert. ✓ marks

\hat{R}_{d}\leq\alpha

Fig. 2: (a) Risk–Coverage Tradeoff curves for CRC-Router and baselines on NIH ChestX-ray14. (b) Prevalence enrichment among escalated cases.

Removed Feature	Macro Cov.	$\Delta$ Cov.
None (full model)	91.3 %	—
${H}_{\bar{p}}$	90.4%	$-$ 0.9%
Mahalanobis	90.0%	$-$ 1.3%
Epistemic	88.2%	$-$ 3.1%
Aleatoric	90.3%	$-$ 1.0%
$\bar{p}$	85.1%	$-$ 6.2%

TABLE III: Ablation study on features in uncertainty vector.

\Delta

Cov. denotes the change in macro coverage relative to the full model.

AI Agent Reliability

AI agent reliability studies whether tool-using systems act correctly, consistently, safely, and recoverably across changing tasks and environments.

See all 339 papers

Agent-as-a-Router: Agentic Model Routing for Coding Tasks
Jun 22, 2026Pengfei Zhou, Zhiwei Tang, Yixing Ma +8AI Coding Agents AI Agent Benchmarks
1National University of Singapore · 2DAMO Academy, Alibaba Group · 3Hupan Lab +3
ToolChain-CRC: Conformal Risk Control for Agentic AI Under Retrieval and Tool-Use Drift
Jun 16, 2026Jeffery Opoku, David BanaheneAI Agent Reliability Distribution Shift
The University of Texas Rio Grande Valley, Edinburg, TX, USA · Florida International University, Miami, FL, USA
AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows
Sep 19, 2026Rudrendu Kumar Paul, Sourav NandyLLM Agent Routing Cost-Aware Inference
Boston University, Boston, MA, USA · University of Texas at Austin, Austin, TX, USA

Jun 22, 2026J/K move · Enter open · S save

Agent-as-a-Router: Agentic Model Routing for Coding Tasks

Pengfei Zhou, Zhiwei Tang, Yixing Ma, Jiasheng Tang+7

1National University of Singapore · 2DAMO Academy, Alibaba Group · 3Hupan Lab+3

AI Coding Agents AI Agent Benchmarks LLM Routing LLM Agent Routing

Open paper AskPDF arXiv

Real-world users typically have access to multiple Large Language Models (LLMs) from different providers, and these LLMs often excel at distinct domains, yet none dominate all. Consequently, routing each task to the most suitable model becomes critical for both performance and cost. Existing routers treat this as a static, one-off classification problem. However, we identify the performance bottleneck for these routers as information deficit: simply augmenting a vanilla LLM router with performance statistics at the task-dimension level yields a 15.3% relative gain, surpassing a heuristic router built on the same dimension-level priors. Motivated by this finding, we propose Agent-as-a-Router, a framework that formalizes routing as a C-A-F loop (Context->Action->Feedback->Context). It closes the information gap by accumulating execution-grounded experience during deployment. We instantiate this framework as ACRouter, composed of an Orchestrator, a Verifier, a Memory module, and introduce CodeRouterBench, an evaluation environment comprising ~10K task instances with verified scores from 8 frontier LLMs, enabling regret-based router comparison on streaming tasks. Experiments show that ACRouter achieves the lowest cumulative regret on in-distribution tasks and generalizes to out-of-distribution agentic-programming tasks, demonstrating that our routing framework actively closes the information gap. Codes and benchmarks are released at https://github.com/LanceZPF/agent-as-a-router.

Abstract

AI Agent Reliability

Explore similar work

Agent-as-a-Router: Agentic Model Routing for Coding Tasks

ToolChain-CRC: Conformal Risk Control for Agentic AI Under Retrieval and Tool-Use Drift

AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows