A simulated social network with LLM agents shows a Q-learning bot can gain about 10% of available followers, with the authors arguing that a small action space and self-observation are key to stable learning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SI 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Synthetic Social Media Influence Experimentation via an Agentic Reinforcement Learning Large Language Model Bot
A simulated social network with LLM agents shows a Q-learning bot can gain about 10% of available followers, with the authors arguing that a small action space and self-observation are key to stable learning.