University of Tehran

Autism resting-state fMRI classifiers rarely generalize across acquisition sites, and many reported accuracies are inflated by data leakage. ASD Neuro Agentic (ANA) has language-model agents propose features from the literature and researcher input while fixed tools perform every calculation; across 1,028 participants from 17 ABIDE I centers it searched pipelines and selected a ComBat-harmonized ensemble of tangent-space connectivity models. In leave-one-center-out testing the ensemble reached an AUC of 0.814 (95% CI, 0.773–0.841), above ASD-DiagNet and ASD-SAENet.

Autism resting-state fMRI classifiers rarely generalize across acquisition sites, and many reported accuracies are inflated by data leakage. ASD Neuro Agentic (ANA) has language-model agents propose features from the literature and researcher input while fixed tools perform every calculation; across 1,028 participants from 17 ABIDE I centers it searched pipelines and selected a ComBat-harmonized ensemble of tangent-space connectivity models. In leave-one-center-out testing the ensemble reached an AUC of 0.814 (95% CI, 0.773–0.841), above ASD-DiagNet and ASD-SAENet.

The authors present PsyCIDRA, a dual-agent framework in which an interviewer agent conducts free-form psychiatric interviews using working notes, expert-written skills, and ICD-11 retrieval, and a diagnostic reasoning agent then receives only the completed transcript and reports hypotheses with supporting, conflicting, and missing evidence, withholding a final hypothesis when evidence is insufficient; across a 53-case evaluation cohort and 81 held-out simulated cases it achieves higher diagnostic agreement than direct prompting, and in a blinded study of 101 human participants it agrees with psychologists on whether to propose a diagnostic hypothesis in 79.6% versus 65.4% of cases.

The authors present PsyCIDRA, a dual-agent framework in which an interviewer agent conducts free-form psychiatric interviews using working notes, expert-written skills, and ICD-11 retrieval, and a diagnostic reasoning agent then receives only the completed transcript and reports hypotheses with supporting, conflicting, and missing evidence, withholding a final hypothesis when evidence is insufficient; across a 53-case evaluation cohort and 81 held-out simulated cases it achieves higher diagnostic agreement than direct prompting, and in a blinded study of 101 human participants it agrees with psychologists on whether to propose a diagnostic hypothesis in 79.6% versus 65.4% of cases.

The study adapts the LLM Uncertainty Head framework to two Persian medical models built on Aya-Expanse-8B, Gaokerena-V and Gaokerena-R; it first observes on a 168-question Iranian medical entrance examination that Gaokerena-V has substantially lower five-run consistency than Aya-Expanse-8B while Gaokerena-R is comparable, then builds Persian claim-level hallucination datasets with 1,600 responses per backbone and trains lightweight claim-level heads on frozen backbone attention maps and token probabilities, obtaining held-out PR-AUCs of 0.4820 and 0.4652 (2.30 and 2.66 times their random baselines) and ROC-AUCs of 0.7852 and 0.7810, with no retrieval or repeated sampling at inference.

The study adapts the LLM Uncertainty Head framework to two Persian medical models built on Aya-Expanse-8B, Gaokerena-V and Gaokerena-R; it first observes on a 168-question Iranian medical entrance examination that Gaokerena-V has substantially lower five-run consistency than Aya-Expanse-8B while Gaokerena-R is comparable, then builds Persian claim-level hallucination datasets with 1,600 responses per backbone and trains lightweight claim-level heads on frozen backbone attention maps and token probabilities, obtaining held-out PR-AUCs of 0.4820 and 0.4652 (2.30 and 2.66 times their random baselines) and ROC-AUCs of 0.7852 and 0.7810, with no retrieval or repeated sampling at inference.