Report
A 7B AI agent reportedly learns to infer a partner’s beliefs and goals during training
A post describing a UC San Diego paper says a separate model scores candidate replies during reinforcement learning.
TLDR
A post describing the UC San Diego paper “Mental-Models for Multi-Agent Systems” says researchers use a model of a partner’s beliefs, intentions and thoughts to score a 7B agent’s candidate replies during reinforcement learning. The post says the trained agent runs without that extra model at deployment.
Combined views
—
1 Source, first seen ago
