EviDx: Evidence-Aware Active Diagnosis with Scaffolded LLM Agents

2026-08-25

AI Summary

EviDx通过构建患者特定的诊断环境和临床诊断框架，结合观察引导的运行时控制，解决了现有大语言模型在医疗诊断中证据获取不足的问题。

Abstract

Clinical diagnosis is an active evidence-seeking process in which clinicians acquire evidence, update competing hypotheses, and decide when the available evidence is sufficient for diagnosis. Yet many medical diagnosis systems built around large language models (LLMs) still formulate diagnosis as static case-to-answer prediction, with limited support for evidence acquisition. Agentic LLMs offer a dynamic alternative through tool use and intermediate diagnostic trajectories, but existing systems often under-specify how patient evidence should be exposed, scaffolded, and controlled at runtime. We introduce EviDx, an evidence-aware active diagnosis framework that pairs patient-specific diagnostic environments with a clinical diagnostic scaffold and an observer-guided runtime harness. In EviDx, $\mathcal{E}$-Synthesis constructs interactive environments from raw clinical cases; the scaffold organizes role-specialized agents, evidence tools, and evolving evidence states; and the harness regulates diagnostic termination by tracking uncertainty and evidence coverage. A 3-level evaluation pyramid assesses execution robustness, reasoning dynamics, and diagnostic outcomes. Experiments show that EviDx improves diagnostic performance and process stability while revealing model-dependent capability boundaries.

Problem

• Clinical Diagnosis
• Evidence Acquisition
• Large Language Models
• Dynamic Diagnosis
• Diagnostic Systems

Innovation

• evidence-aware active diagnosis
• LLM agents
• diagnostic scaffold
• runtime harness