PrivMeSA assigns a local agent to manage each patient encounter and hold multi-turn consultations with remote specialist models.
Local clinical agents learn to consult remote models without identifying patients
PrivMeSA combines reinforcement-learned disclosure controls with local lesson memory to preserve remote expertise while reducing cumulative privacy risks.
Academic
Dannong Wang · Yuran Zhang · Bian Sun · Alex Stinard · Yuzhang Shang · Song Wang · +1 more
University of Central Florida · Université de Montréal
Research Digest··2 min read
Thread:Multi-Agent Coordination
Wang and colleagues developed a multi-agent clinical system in which a local model selectively consults remote specialists while controlling what patient information leaves the institution.
Why this paper
From University of Central Florida and Université de Montréal · Part of Multi-Agent Coordination, now 34 papers
In one line
PrivMeSA reduces patient re-identification risk to 0% and improves task accuracy by up to 15.8 percentage points.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§