MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents
MedCUA-Bench is a newly introduced benchmark designed specifically for clinical computer-use agents. It aims to address the lack of reliable testing environments for medical software by covering 18 clinical scenarios across 10 medical domains. The benchmark reveals significant gaps in the performance of current agents when applied to real clinical interfaces.
- ▪MedCUA-Bench focuses on automating repetitive screen-based clinical work.
- ▪It includes 18 clinical scenarios reconstructed from real product manuals.
- ▪The best closed-source model achieved only 54.2% success on the benchmark.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2606.03203 |
| Publication time | Wed, 03 Jun 2026 00:00:00 -0400 |
| Retrieval time | 2026-06-03T04:11:55.408Z |
| Last seen | 2026-06-03T04:11:55.408Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | X0gGDPjm110w |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2606.03203 (cs) [Submitted on 2 Jun 2026] Title:MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents Authors:Jia Yu, Zilong Wang, Xinyang Jiang, Dongsheng Li, Shuo Wang View a PDF of the paper titled MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents, by Jia Yu and 4 other authors View PDF HTML (experimental) Abstract:Computer-use agents could automate repetitive screen-based clinical work, but their reliability in medical graphical user interfaces remains largely unvalidated.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
