SOTOPIA-$\pi$: Interactive Learning of Socially Intelligent Language Agents

arXiv:2403.08715v1 Announce Type: new
Abstract: Humans learn social skills through both imitation and social interaction. This social learning process is largely understudied by existing research on building language agents. Motivated by this gap, we propose an interactive learning method, SOTOPIA-$\pi$, improving the social intelligence of language agents. This method leverages behavior cloning and self-reinforcement training on filtered social interaction data according to large language model (LLM) ratings. We show that our training method allows a 7B LLM to reach the …

abstract agents arxiv behavior building cloning cs.cl gap humans intelligence intelligent interactive language learn process research skills social through type