Tag
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.
This paper proposes a novel preference estimation method that integrates natural language information from LLMs into a structured Bayesian opponent modeling framework for multi-agent negotiation. The approach leverages LLMs to extract qualitative cues from utterances and convert them into probabilistic formats, demonstrating improved agreement rates and preference estimation accuracy on multi-party negotiation benchmarks.
OpenAI presents LOLA (Learning with Opponent-Learning Awareness), a multi-agent reinforcement learning method where agents shape the anticipated learning of other agents. The approach demonstrates emergence of cooperation in iterated prisoner's dilemma and convergence to Nash equilibrium in game-theoretic settings.