mlsanityData to 14 Oct 2026

When Numbers Start Talking: Implicit Numerical Coordination Among LLM-Based Agents

arXiv 2601.03846 ↗First posted 7 Jan 2026cs.MA cs.AIcited by 2

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

LLMs-based agents increasingly operate in multi-agent environments where strategic interaction and coordination are required. While existing work has largely focused on individual agents or on interacting agents sharing explicit communication, less is known about how interacting agents coordinate implicitly. In particular, agents may engage in covert communication, relying on indirect or non-linguistic signals embedded in their actions rather than on explicit messages. This paper presents a game-theoretic study of covert communication in LLM-driven multi-agent systems. We analyse interactions across four canonical game-theoretic settings under different communication regimes, including explicit, restricted, and absent communication. Considering heterogeneous agent personalities and both one-shot and repeated games, we characterise when covert signals emerge and how they shape coordination and strategic outcomes.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 21 of its 51 references that are in the map. First posted on arXiv 7 Jan 2026.

Builds on

21 of 51 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Strategic Communication and Language Bias in Multi-Agent LLM Coordination30 Jul
  2. 2025FAIRGAME: a Framework for AI Agents Bias Recognition using Game Theory19 Apr
  3. 2025Inducing Personality in LLM-Based Honeypot Agents: Measuring the Effect on Human-Like Agenda Generation25 Mar
  4. 2025Will Systems of LLM Agents Cooperate: An Investigation into a Social Dilemma27 Jan
  5. 2024AFSPP: Agent Framework for Shaping Preference and Personality with Large Language Models5 Jan
  6. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 15

  1. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,729
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  3. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Modelscited by 341
  4. 2025Multi-Agent Risks from Advanced AIcited by 163
  5. 2024Secret Collusion among AI Agents: Multi-Agent Deception via Steganographycited by 113
  6. 2025Subliminal Learning: Language models transmit behavioral traits via hidden signals in datacited by 95
  7. 2025Latent Collaboration in Multi-Agent Systemscited by 73
  8. 2024Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?cited by 63
  9. 2024UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulationcited by 31
  10. 2025Towards Mechanistic Interpretability of Graph Transformers via Attention Graphscited by 13
  11. 2024Generative AI for Game Theory-based Mobile Networkingcited by 12
  12. 2025Media and responsible AI governance: a game-theoretic and LLM analysiscited by 12
3 more
  1. 2024Surprising gender biases in GPTcited by 8
  2. 2024Large Language Models' Detection of Political Orientation in Newspaperscited by 5
  3. 2023Utility Fairness in Contextual Dynamic Pricing with Demand Learningcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphscited by 20
  2. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systemscited by 6

Similar, not cited

Close in wording, no citation either way

  1. 2026Multi-Agent Strategic Games with LLMs
  2. 2025Communication and Verification in LLM Agents towards Collaboration under Information Asymmetry
  3. 2025Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems
  4. 2026Deception and Communication in Autonomous Multi-Agent Systems: An Experimental Study with Among Us
  5. 2025Emergent Coordination in Multi-Agent Language Models
  6. 2025Do LLMs Strategically Reveal, Conceal, and Infer Information? A Theoretical and Empirical Analysis in The Chameleon Game
  7. 2025AsymPuzl: An Asymmetric Puzzle for multi-agent cooperation
  8. 2026Be Careful Who You Trust: Coordination Dynamics under Corrupted Communication in LLM Multi-Agent Games