CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games

TL;DR

CoMet is a framework that improves large language models' ability to interpret and generate metaphors, enabling more strategic and covert communication in multi-agent language games.

Contribution

We introduce CoMet, a novel metaphor processing framework that enhances LLMs' metaphor understanding and application for strategic multi-agent interactions.

Findings

Significantly improves metaphor-based covert communication.

Enhances strategic interaction in multi-agent language games.

Demonstrates effectiveness on Undercover and Adversarial Taboo games.

Abstract

Metaphors are a crucial way for humans to express complex or subtle ideas by comparing one concept to another, often from a different domain. However, many large language models (LLMs) struggle to interpret and apply metaphors in multi-agent language games, hindering their ability to engage in covert communication and semantic evasion, which are crucial for strategic communication. To address this challenge, we introduce CoMet, a framework that enables LLM-based agents to engage in metaphor processing. CoMet combines a hypothesis-based metaphor reasoner with a metaphor generator that improves through self-reflection and knowledge integration. This enhances the agents' ability to interpret and apply metaphors, improving the strategic and nuanced quality of their interactions. We evaluate CoMet on two multi-agent language games - Undercover and Adversarial Taboo - which emphasize Covert Communication and Semantic Evasion. Experimental results demonstrate that CoMet significantly enhances the agents' ability to communicate strategically using metaphors.