---
title: "LLM-Orchestrated Diagnose–Plan–Treat for Mixed-Degradation CT Reconstruction"
authors:
  - "Yongqiang Huang"
  - "Yingyu Chen"
  - "Fengzhi Xu"
  - "Tao Wang"
  - "Wenjun Xia"
  - "Hongming Shan"
  - "Yi Zhang"
doi: "10.24963/ijcai.2026/17"
url: "https://ijcai.org/proceedings/2026/17"
pdf: "https://ijcai.org/proceedings/2026/0017.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "145-153"
track: "Main Track"
keywords:
  - "Computer Vision: Biomedical image analysis"
  - "Agent-based and Multi-agent Systems: Coordination and cooperation"
---

# LLM-Orchestrated Diagnose–Plan–Treat for Mixed-Degradation CT Reconstruction

Yongqiang Huang, Yingyu Chen, Fengzhi Xu, Tao Wang, Wenjun Xia, Hongming Shan, Yi Zhang

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 145-153. DOI: [10.24963/ijcai.2026/17](https://doi.org/10.24963/ijcai.2026/17)

## Abstract

Clinical Computed Tomography (CT) reconstruction often faces mixed degradations, where quantum noise, streak artifacts, and geometric distortions co-occur with various compositions and severities. Recently, all-in-one frameworks have outperformed traditional single-task models through degradation-specialized modulation mechanisms. However, attempting to resolve these mixed degradations simultaneously forces the model into suboptimal trade-offs, failing to balance conflicting reconstruction objectives. Our empirical study shows that decomposing CT reconstruction into a sequence of ordered steps effectively mitigates this conflict, with the execution order being a critical performance factor. Leveraging this insight, we propose AgenticCT, an LLM-orchestrated multi-agent framework designed to autonomously plan the optimal reconstruction trajectory. Specifically, AgenticCT operates through a diagnose-plan-treat workflow: a Supervisor Agent explicitly estimates a structured degradation state; a Planner Agent then selects a topology-optimized execution order conditioned on this state; and a library of Processor Agents sequentially executes the trajectory to achieve high-fidelity reconstruction.  Extensive experiments demonstrate that AgenticCT consistently improves reconstruction fidelity across single and mixed degradations, and generalizes better to out-of-distribution datasets compared with strong specialized and all-in-one baselines. Code is available at: https://github.com/yqhuang2912/AgenticCT.