Large language model (LLM) systems can now generate complete research manuscripts, yet their reliability in clinical medicine - where citation accuracy and reporting standards carry direct consequences - has not been systematically assessed. We introduce MedResearchBench, a benchmark of three clinical epidemiology tasks built on NHANES data, and use it to evaluate six AI research systems across six quality dimensions. Evaluation combines programmatic citation verification, rule-based reporting compliance checks, and multi-model LLM judging, providing a more discriminative assessment than conventional single-judge approaches. Citation integrity emerged as the decisive quality dimension. Hallucination rates ranged from 2.9% to 36.8% across systems, and a hard-rule threshold on per-task citation scores capped four of six systems' total scores at the penalty ceiling. Adding a multi-agent citation verification and repair pipeline to the best-performing system improved its citation integrity score from 40.0 to 90.9 and raised the weighted total from 68.9 to 81.8. Strikingly, a single-model evaluation ranked this system last (55.5), while our three-tier framework ranked it first (81.8) - a complete reversal that exposes the limitations of subjective LLM-only evaluation. These results suggest that programmatic citation verification should be a core metric in future evaluations of AI scientific writing systems, and that multi-agent quality assurance can bridge the gap between fluent text generation and trustworthy scholarship.

The authors have declared no competing interest.

Funding: Shanghai Municipal Science and Technology Commission Medical Innovation Research。 Program ：23Y31920200

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

The study used ONLY openly available human data that were publicly available before the initiation of the study. The original source data can be located and downloaded at: NHANES (National Health and Nutrition Examination Survey): https://wwwn.cdc.gov/nchs/nhanes/ No application, screening, registration, or restricted-access request was required to access the source data.

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

All data referred to in this manuscript are publicly available. Raw NHANES data are available at https://wwwn.cdc.gov/nchs/nhanes/, and all study-generated materials (evaluation scripts, results packages, and generated manuscripts) are available at https://github.com/TerryFYL/ai-research-army.

https://github.com/TerryFYL/ai-research-army

https://wwwn.cdc.gov/nchs/nhanes/