About this paper
SkinMind is a multimodal agentic retrieval framework that iteratively probes a large dermatology knowledge graph to gather textual and visual evidence, yielding more accurate answers to dermatology visual questions than direct answering and other retrieval methods.
Reliable dermatology AI requires access to verifiable evidence distributed across heterogeneous textual and visual sources. However, conventional retrieval-augmented generation (RAG) typically relies on one-shot retrieval from flat corpora, limiting its ability to adapt retrieval granularity, explore multi-hop relations, and integrate multimodal clinical evidence. We introduce SkinMind, a multimodal agentic RAG framework that equips policy models with human-inspired graph probing for autonomous evidence seeking. SkinMind organizes retrieval as an iterative interaction between an orchestrator and a graph environment. Through eight hierarchical graph-probing tools, the orchestrator…
retrieval-augmented generation (RAG)multimodal agentic RAGpolicy modelsgraph probingorchestratorgraph environmenthierarchical graph-probing toolsmulti-hop relationsprogressive-disclosureretrieval modality
- Upvotes
- 4
- Authors
- 14
- Published
- Nov 6, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
SkinMind: Equipping Agentic RAG with Human-Inspired Graph Probing for Reliable Dermatology AI was first seen on Hugging Face · Daily papers on Nov 11, 2026. Since then it has appeared in 7 checks on 1 different day. Its best position was #25 of 30, reached on Nov 11, 13:28 UTC. It dropped off the list after Nov 11, 17:28 UTC.