@inproceedings{tan-etal-2026-graphdx,
    title = "{G}raph{D}x: A Cost-Aware Knowledge-Enhanced Multi-Agent Framework for Sequential Diagnosis",
    author = "Tan, Shaoting  and
      Liu, Ning  and
      Du, Yuntao  and
      Wei, Shuyue  and
      Shuai, Wu  and
      Li, Qian  and
      Xu, Yanyu  and
      Zhang, Wei  and
      Cui, Lizhen  and
      Yuan, Haitao",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1092/",
    pages = "21721--21736",
    ISBN = "979-8-89176-395-1",
    abstract = "Sequential diagnosis requires balancing diagnostic accuracy against resource costs through iterative information gathering. Existing Large Language Model (LLM) approaches exhibit a critical knowledge-reasoning gap: despite encoding extensive medical knowledge, they struggle to reason systematically under cost constraints, often resorting to excessive testing. We propose GraphDx, a knowledge-enhanced framework with two core innovations. First, we design an automated pipeline that leverages LLMs to construct Medical Diagnosis Knowledge Graphs (MDKGs) with quantized typicality, action-centric topology, and dual-objective attributes for both diagnostic relevance and cost-sensitivity. Second, we introduce three collaborative agents (Perception, Reasoning, and Decision) where the Perception and Decision Agents handle language understanding and generation, while the Reasoning Agent performs deterministic evidence scoring and cost-aware planning on the MDKG. Experiments on MedQA and MIMIC-IV across three LLM backbones (DeepSeek-V3, Kimi-k2, Llama-3.3) show that GraphDx improves diagnostic success rates from 50{--}68{\%} to 79{--}93{\%} while reducing test costs by 20{--}54{\%}, providing a robust, economical, and interpretable solution for automated clinical diagnosis."
}