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

arXiv: https://arxiv.org/abs/2505.18218 · HTML: https://mlsanity.com/paper/2505.18218/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 34 references that are in the map.
- First posted on arXiv 23 May 2025.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 14 of 14)

- [Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game](https://mlsanity.com/paper/2310.18940/) (2023)
- [Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading](https://mlsanity.com/paper/2310.05029/) (2023)
- [Self-playing Adversarial Language Game Enhances LLM Reasoning](https://mlsanity.com/paper/2404.10642/) (2024)
- [A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning](https://mlsanity.com/paper/2406.05804/) (2024)
- [Testing the Ability of Language Models to Interpret Figurative Language](https://mlsanity.com/paper/2204.12632/) (2022)
- [MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration](https://mlsanity.com/paper/2311.08562/) (2023)
- [Welfare Diplomacy: Benchmarking Language Model Cooperation](https://mlsanity.com/paper/2310.08901/) (2023)
- [Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy](https://mlsanity.com/paper/2407.06813/) (2024)
- [Enhancing Zero-Shot Chain-of-Thought Reasoning in Large Language Models through Logic](https://mlsanity.com/paper/2309.13339/) (2023)
- [Metaphor Understanding Challenge Dataset for LLMs](https://mlsanity.com/paper/2403.11810/) (2024)
- [Emergence of Pragmatics from Referential Game between Theory of Mind Agents](https://mlsanity.com/paper/2001.07752/) (2020)
- [Metaphor Detection via Explicit Basic Meanings Modelling](https://mlsanity.com/paper/2305.17268/) (2023)
- [Adversarial Language Games for Advanced Natural Language Intelligence](https://mlsanity.com/paper/1911.01622/) (2019)
- [Verifying Claims About Metaphors with Large-Scale Automatic Metaphor Identification](https://mlsanity.com/paper/2404.01029/) (2024)

## Built on by (most cited first, 7 of 7)

- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [Beyond Self-Interest: Modeling Social-Oriented Motivation for Human-like Multi-Agent Interactions](https://mlsanity.com/paper/2603.13890/) (2026)
- [The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation](https://mlsanity.com/paper/2606.03032/) (2026)
- [SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems](https://mlsanity.com/paper/2609.00595/) (2026)
- [Towards High-Level Semantic Intelligence](https://mlsanity.com/paper/2607.24082/) (2026)
- [Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations](https://mlsanity.com/paper/2609.26927/) (2026)
- [When Numbers Start Talking: Numerical Signalling and Strategic Behaviour Among LLMs](https://mlsanity.com/paper/2610.03033/) (2026)

## Abstract (arXiv)

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.