6/6 Thanks to our amazing students and collaborators! @vcalhoun.bsky.social @trendscenter.bsky.social

📄 Paper: openreview.net/forum?id=mV0...
💻 Code: github.com/trendscenter...
📆 Poster: Dec 2, 15:25 PST

5/ The meta-review agent achieved 78% accuracy in binary classification, remarkably matching the performance of a human evaluator. This system may serve as an interpretable, scalable decision-support tool, offering insights into patients' mental health conditions.

4/ The quantitative assessment agent used an embedding-based few-shot prompting approach to predict symptom-specific scores, achieving an average MAE of 0.619, compared with 0.796 for zero-shot prompting.

3/ The qualitative assessment agent produced specific, coherent, complete, and clinically meaningful assessments, confirmed by both a human reviewer and the judge agent. The feedback loop effectively improved all evaluation metrics.

2/ The system includes four agents: (1) a qualitative assessment agent that identifies risk factors, (2) a judge agent that evaluates qualitative assessment, (3) a quantitative assessment agent that predicts clinical scores, (4) a meta-review agent that integrates information and estimates severity.