mlsanityData to 7 Oct 2026

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

arXiv 2505.18218 ↗First posted 23 May 2025cs.CL cs.AIcited by 6

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

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.

Key facts. Cited by 6 papers in the map (data through 7 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.

Builds on

14 of 34 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy9 Jul
  2. 2023MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration14 Nov
  3. 2023Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game29 Oct

Other references · 11

  1. 2023Walking Down the Memory Maze: Beyond Context Limit through Interactive Readingcited by 129
  2. 2024Self-playing Adversarial Language Game Enhances LLM Reasoningcited by 80
  3. 2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learningcited by 74
  4. 2022Testing the Ability of Language Models to Interpret Figurative Languagecited by 67
  5. 2023Welfare Diplomacy: Benchmarking Language Model Cooperationcited by 43
  6. 2023Enhancing Zero-Shot Chain-of-Thought Reasoning in Large Language Models through Logiccited by 34
  7. 2024Metaphor Understanding Challenge Dataset for LLMscited by 30
  8. 2020Emergence of Pragmatics from Referential Game between Theory of Mind Agentscited by 17
  9. 2023Metaphor Detection via Explicit Basic Meanings Modellingcited by 12
  10. 2019Adversarial Language Games for Advanced Natural Language Intelligencecited by 6
  11. 2024Verifying Claims About Metaphors with Large-Scale Automatic Metaphor Identificationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  2. 2026Beyond Self-Interest: Modeling Social-Oriented Motivation for Human-like Multi-Agent Interactionscited by 2
  3. 2026The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberationcited by 1
  4. 2026SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systemscited by 1
  5. 2026Towards High-Level Semantic Intelligencecited by 0
  6. 2026Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Evaluating Creativity and Deception in Large Language Models: A Simulation Framework for Multi-Agent Balderdash
  2. 2026LinguaGame: A Linguistically Grounded Game-Theoretic Paradigm for Multi-Agent Dialogue Generation
  3. 2025LLMs as Deceptive Agents: How Role-Based Prompting Induces Semantic Ambiguity in Puzzle Tasks
  4. 2026MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs
  5. 2025Communication and Verification in LLM Agents towards Collaboration under Information Asymmetry
  6. 2023Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models
  7. 2025The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind
  8. 2025Scheming Ability in LLM-to-LLM Strategic Interactions