# EviDx: Evidence-Aware Active Diagnosis with Scaffolded LLM Agents

arXiv: https://arxiv.org/abs/2608.24570 · HTML: https://mlsanity.com/paper/2608.24570/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 11 of its 38 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 11 of 11)

- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [Benchmarking Retrieval-Augmented Generation for Medicine](https://mlsanity.com/paper/2402.13178/) (2024)
- [AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments](https://mlsanity.com/paper/2405.07960/) (2024)
- [MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding](https://mlsanity.com/paper/2501.18362/) (2025)
- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions](https://mlsanity.com/paper/2402.18060/) (2024)
- [MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic Workflow](https://mlsanity.com/paper/2503.18968/) (2025)
- [MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents](https://mlsanity.com/paper/2501.14654/) (2025)
- [ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction](https://mlsanity.com/paper/2508.00500/) (2025)
- [A Knowledge-driven Adaptive Collaboration of LLMs for Enhancing Medical Decision-making](https://mlsanity.com/paper/2509.14998/) (2025)
- [AutoMedic: An Automated Evaluation Framework for Clinical Conversational Agents with Medical Dataset Grounding](https://mlsanity.com/paper/2512.10195/) (2025)

## Built on by (most cited first, 2 of 2)

- [MIRROR: From Imitation to Internalization in LLM Personalization](https://mlsanity.com/paper/2610.09795/) (2026)
- [SHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces](https://mlsanity.com/paper/2610.18025/) (2026)

## Abstract (arXiv)

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, 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.