Tag
A counterfactual simulator for marketing decisions combining structural causal models, Hawkes processes, and LLM agents; allows querying 'what-if' scenarios before committing budget. Open source on GitHub.
This paper introduces Structured Opponent Modeling (SOM), a framework using Structural Causal Models to decouple opponent representation from prediction for LLM-based agents in multi-agent environments. The method improves prediction accuracy and strategic decision-making by leveraging explicit causal structures rather than implicit contextual reasoning.