# Emulating Clinician Cognition via Self-Evolving Deep Clinical Research

arXiv: https://arxiv.org/abs/2603.10677 · HTML: https://mlsanity.com/paper/2603.10677/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 52 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Builds on (most cited first, 16 of 16)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents](https://mlsanity.com/paper/2405.02957/) (2024)
- [Memory Injection Attacks on LLM Agents via Query-Only Interaction](https://mlsanity.com/paper/2503.03704/) (2025)
- [Towards Accurate Differential Diagnosis with Large Language Models](https://mlsanity.com/paper/2312.00164/) (2023)
- [Diagnostic Reasoning Prompts Reveal the Potential for Large Language Model Interpretability in Medicine](https://mlsanity.com/paper/2308.06834/) (2023)
- [Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding](https://mlsanity.com/paper/2305.12031/) (2023)
- [Sequential Diagnosis with Language Models](https://mlsanity.com/paper/2506.22405/) (2025)
- [An Agentic System for Rare Disease Diagnosis with Traceable Reasoning](https://mlsanity.com/paper/2506.20430/) (2025)
- [MACD: Multi-Agent Clinical Diagnosis with Self-Learned Knowledge for LLM](https://mlsanity.com/paper/2509.20067/) (2025)

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

- [The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement](https://mlsanity.com/paper/2609.11873/) (2026)
- [CDEG: Learning Decision-Critical Evidence for Long-Horizon Diagnostic Agents](https://mlsanity.com/paper/2608.22899/) (2026)

## Abstract (arXiv)

Clinical diagnosis is a complex cognitive process, grounded in dynamic cue acquisition and continuous expertise accumulation. Yet most current artificial intelligence (AI) systems are misaligned with this reality, treating diagnosis as single-pass retrospective prediction while lacking auditable mechanisms for governed improvement. We developed DxEvolve, a self-evolving diagnostic agent that bridges these gaps through an interactive deep clinical research workflow. The framework autonomously requisitions examinations and continually externalizes clinical experience from increasing encounter exposure as diagnostic cognition primitives. On the MIMIC-CDM benchmark, DxEvolve improved diagnostic accuracy by 11.2% on average over backbone models and reached 90.4% on a reader-study subset, comparable to the clinician reference (88.8%). DxEvolve improved accuracy on an independent external cohort by 10.2% (categories covered by the source cohort) and 17.1% (uncovered categories) compared to the competitive method. By transforming experience into a governable learning asset, DxEvolve supports an accountable pathway for the continual evolution of clinical AI.