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

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.
DiseaseAccept -AllMaxProb [ 20 ]MCD-MI [ 21 ]Conformal Pred. [ 19 ]CRC-RouterRisk Red. †\dagger
Atelectasis17.0%5.4%10.6%11.9%3.9%✓↓\downarrow 77%
Cardiomegaly3.8%✓1.5%✓1.3%✓1.1%✓3.8%✓–
Consolidation18.1%9.8%17.8%9.6%4.4%✓↓\downarrow 76%
Edema2.8%✓0.8%✓0.8%✓1.0%✓2.8%✓–
Effusion14.8%5.1%9.3%9.6%4.4%✓↓\downarrow 70%
Emphysema2.3%✓1.4%✓0.8%✓0.9%✓2.3%✓–
TABLE I: Per-disease risk ( R^d\hat{R}_{d} ) across routing methods ( α=5%\alpha=5\% ). All selective methods are matched to ∼{\sim} 91% macro coverage. Best results among selective methods are highlighted in bold. ✓ indicates R^d≤α\hat{R}_{d}\leq\alpha . †\dagger Relative reduction of CRC-Router risk compared to Accept-All; “–” indicates the Accept-All risk is already below α\alpha .
NIH ChestX-ray14 [ 22 ]CheXpert [ 23 ]
DiseaseMedRAX [ 10 ]+CR * (TTA)+CR * (MoE)DiseaseMedRAX [ 10 ]+CR * (TTA)
Atelectasis6.6%4.7%✓4.0%✓Enl. Cardiomed.57.6%4.2%✓
Cardiomegaly12.9%3.6%✓3.7%✓Cardiomegaly51.3%4.7%✓
Consolidation9.6%6.6%3.4%✓Lung Opacity30.1%4.7%✓
Edema6.5%6.2%2.9%✓Lung Lesion1.5%✓3.9%✓
Effusion14.5%5.9%4.3%✓Edema19.4%4.3%✓
TABLE II: Per-disease wrong-accept risk ( R^d\hat{R}_{d} ) for MedRAX integration at α=5%\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 R^d≤α\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 FeatureMacro Cov.Δ\Delta Cov.
None (full model)91.3 %—
Hpˉ{H}_{\bar{p}}90.4%−- 0.9%
Mahalanobis90.0%−- 1.3%
Epistemic88.2%−- 3.1%
Aleatoric90.3%−- 1.0%
pˉ\bar{p}85.1%−- 6.2%
TABLE III: Ablation study on features in uncertainty vector. Δ\Delta Cov. denotes the change in macro coverage relative to the full model.
More in this topic

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

Explore similar work

CardsList
Jun 22, 2026

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

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.

Pengfei Zhou, Zhiwei Tang, Yixing Ma +8

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

AI Coding AgentsAI Agent BenchmarksLLM RoutingLLM Agent Routing
AskPDF
Jun 16, 2026

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

Modern AI agents retrieve documents, call tools, check intermediate information, and then produce a final answer or action. This creates a risk-control problem that is not visible from the final answer alone. A final response may look acceptable even when the retrieval was weak, a tool output was wrong, or an earlier step was unsupported. We propose ToolChain-CRC, a conformal risk-control method for retrieval-augmented and tool-using agents under drift. The method treats each agent run as a full trajectory of actions, observations, and final output. It builds step-level risk scores, combines them into a trajectory risk score, calibrates an accept-or-intervene rule, and adds an anytime alarm that can stop risky runs before the final answer. We prove trajectory-level risk control under exchangeable calibration runs, give a drift-aware extension with auditable constants, and prove an anytime escalation rule through a supermartingale construction. Experiments cover synthetic tool-chain drift, RAG/tool-use stress tests, public SQuAD-derived retrieval tasks, an API-free agentic QA case study, ablations, target-risk sensitivity checks, 20-seed robustness checks, a drift-margin audit, and a live RAG/tool-use agent benchmark. Across these settings, final-answer-only calibration can miss retrieval and tool failures, while trajectory-level calibration keeps accepted-trajectory risk below the target.

Jeffery Opoku, David Banahene

The University of Texas Rio Grande Valley, Edinburg, TX, USA · Florida International University, Miami, FL, USA

AI Agent ReliabilityDistribution ShiftAI ControlTool-Using AgentsConformal Risk ControlAgentic RAG+1
AskPDF
Sep 19, 2026

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

Enterprise agentic systems that route every trajectory step to a frontier model waste 60-80% of their inference budget on subtasks that smaller models handle equally well. Existing routing solutions optimize single-turn query assignment but ignore a property unique to agentic workflows: subtask complexity varies widely within a single trajectory. A planning step may require frontier-class reasoning while a subsequent formatting step needs only a 7B model. We formalize step-level model routing as a sequential assignment problem over agent trajectories and propose AgentRouter, a lightweight classifier (12M parameters, <5ms overhead per step on an A100 GPU) that maps each trajectory step to one of four model tiers using five features extractable at routing time. Trained on 50,000 annotated agent trajectory steps spanning planning, coding, research, and data analysis tasks, AgentRouter achieves 72% cost reduction relative to frontier-only baselines, retaining 97.3% of frontier-only quality (less than 3% degradation in end-to-end task completion); per-step routing accuracy reaches 91% on minimal-complexity steps and 85% on efficient-tier steps, with 76-82% on the harder mid-range and frontier tiers. On the same benchmarks, RouteLLM and FrugalGPT (applied per-step) achieve only 31% and 44% cost reduction respectively, because their single-turn training signal misses trajectory-level quality dependencies.

Rudrendu Kumar Paul, Sourav Nandy

Boston University, Boston, MA, USA · University of Texas at Austin, Austin, TX, USA

LLM Agent RoutingCost-Aware InferenceAgentic Workflows
AskPDF