# Can Agents Distinguish Visually Hard-to-Separate Diseases in a Zero-Shot Setting? A Pilot Study

arXiv: https://arxiv.org/abs/2602.22959 · HTML: https://mlsanity.com/paper/2602.22959/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)
- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 18 of 18)

- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning](https://mlsanity.com/paper/2502.19634/) (2025)
- [When combinations of humans and AI are useful: A systematic review and meta-analysis](https://mlsanity.com/paper/2405.06087/) (2024)
- [A Survey of LLM-based Agents in Medicine: How far are we from Baymax?](https://mlsanity.com/paper/2502.11211/) (2025)
- [Learning Hierarchical Attention for Weakly-supervised Chest X-Ray Abnormality Localization and Diagnosis](https://mlsanity.com/paper/2112.12349/) (2021)
- [RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models](https://mlsanity.com/paper/2411.00299/) (2024)
- [Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skills](https://mlsanity.com/paper/2410.04253/) (2024)
- [Automation Bias in AI-Assisted Medical Decision-Making under Time Pressure in Computational Pathology](https://mlsanity.com/paper/2411.00998/) (2024)
- [PASS: Probabilistic Agentic Supernet Sampling for Interpretable and Adaptive Chest X-Ray Reasoning](https://mlsanity.com/paper/2508.10501/) (2025)
- [Knowing or Guessing? Robust Medical Visual Question Answering via Joint Consistency and Contrastive Learning](https://mlsanity.com/paper/2508.18687/) (2025)
- [Hallucination Filtering in Radiology Vision-Language Models Using Discrete Semantic Entropy](https://mlsanity.com/paper/2510.09256/) (2025)
- [Anatomical Region-Guided Contrastive Decoding: A Plug-and-Play Strategy for Mitigating Hallucinations in Medical VLMs](https://mlsanity.com/paper/2512.17189/) (2025)

## Built on by (most cited first, 1 of 1)

- [From Clinical Intent to Clinical Model: Autonomous Coding-Agents for Clinician-driven AI Development](https://mlsanity.com/paper/2604.17110/) (2026)

## Abstract (arXiv)

The rapid progress of multimodal large language models (MLLMs) has led to increasing interest in agent-based systems. While most prior work in medical imaging concentrates on automating routine clinical workflows, we study an underexplored yet clinically significant setting: distinguishing visually hard-to-separate diseases in a zero-shot setting. We benchmark representative agents on two imaging-only proxy diagnostic tasks, (1) melanoma vs. atypical nevus and (2) pulmonary edema vs. pneumonia, where visual features are highly confounded despite substantial differences in clinical management. We introduce a multi-agent framework based on contrastive adjudication. Experimental results show improved diagnostic performance (an 11-percentage-point gain in accuracy on dermoscopy data) and reduced unsupported claims on qualitative samples, although overall performance remains insufficient for clinical deployment. We acknowledge the inherent uncertainty in human annotations and the absence of clinical context, which further limit the translation to real-world settings. Within this controlled setting, this pilot study provides preliminary insights into zero-shot agent performance in visually confounded scenarios.