# Google DeepMind trains a model on simulated psychiatric intakes with RL

> Original title: New Google DeepMind paper shows that training a model with RL on simulated patients made it a better psychiatric intake interviewer, as j...

- Source: Rohan Paul
- Published: 2026-10-31T15:23:00.000Z
- Bad Influence: https://badinfluence.news/items/hd5qh45qk1jd69dckipi3bmcu
- Original: https://x.com/rohanpaul_ai/status/2116551519034048861

## Summary

Google DeepMind trained Gemini 3.1 Flash-Lite with multi-turn reinforcement learning against simulated patients who reveal key facts only after rapport and targeted questions. Psychiatrists judged the trained agent better than its identically prompted base model in 76.7% of 60 matched case pairs. On 256 adversarial cases, failure to escalate acute risk fell from 30.5% to 12.9%, and the authors recommend keeping clinicians supervising.

## Post

New Google DeepMind paper shows that training a model with RL on simulated patients made it a better psychiatric intake interviewer, as judged by psychiatrists.

training on simulated psychiatric intakes cut missed escalations of acute risk from 30.5% to 12.9% in adversarial cases.

In psychiatry, the intake interview is a main diagnostic tool, and key facts often surface only through trust and careful questions. Most conversational medical AI evaluations have left psychiatric cases out.

They trained Gemini 3.1 Flash-Lite with multi-turn RL against simulated patients who reveal key facts only after rapport and targeted questions. Then 32 psychiatrists role-played patients, while 15 others graded the transcripts blind.

The trained agent beat its identically prompted base model in 76.7% of 60 matched case pairs. On 256 adversarial cases, it failed to escalate acute risks 12.9% of the time, down from 30.5%.

If you build health agents, train them on simulated conversations, but keep clinicians supervising, since about 1 in 8 adversarial crises went unescalated.

– arxiv. org/abs/2610.40476

Title: "Training language models in simulation for psychiatric intake"

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHV9ynLObsAAMft_.png&mode=thumb&exp=1793664000&sig=2ba06884acba5373)