{"id":"doi:10.1056/aidbp2500144","kind":"article","title":"MedAgentBench: A Virtual EHR Environment to Benchmark Medical LLM Agents","authors":["Yixing Jiang","Kameron Collin Black","Gloria Geng","Danny Park","James Zou","Andrew Y. Ng","Jonathan H. Chen"],"author_count":7,"year":2025,"published":"2025-08-14","venue":"NEJM AI","cited_by":66,"doi":"10.1056/aidbp2500144","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1056/aidbp2500144","archive_url":"https://space-kitty.com/papers/doi:10.1056/aidbp2500144","updated":null,"pmid":"42932685","pmcid":null,"openalex_id":"W4413801638","pdf_url":"https://ai.nejm.org/doi/pdf/10.1056/AIdbp2500144","abstract":null,"abstract_license":null,"license":null,"is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Artificial Intelligence in Healthcare and Education"],"details":null,"provenance":"openalex","attribution":"Metadata and citation counts: OpenAlex (CC0).","topics":[{"slug":"ai-agents","name":"LLM Agents & Tool Use","domain_slug":"ai"}],"cited_in_dossiers":[]}