Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game
On the map: LLM agents and tool use → Social simulation and multi-agent debate
Abstract (arXiv)
LLMs agents are increasingly used in multi-agent settings, yet their behaviour in sustainability games remains largely unexplored. This work investigates whether lying can emerge among LLM agents in a competitive sustainability game in which agents are informed that common resources can regenerate, although regeneration does not actually occur. We develop an agent-based model of a sustainability game in which agents manage industrial, military, and ecological resources, and interact through a network. LLM agents can observe neighbours' status, declare future attacks, receive permission to lie, and access reputation information, while rule-based agents provide an interpretable behavioural baseline. The results show that neighbour information strongly changes system dynamics, increasing attacks while improving biosphere retention and coexistence. Also, the presence of future declarations reduce extinction risk without suppressing conflict. Behaviourally, deception emerges even when agents are not explicitly allowed to lie, and explicit permission mainly increases bluffing and diversion rather than direct backstabbing. Finally, the presence of reputation memory and information about the current biosphere level reduces system ecological depletion. These findings suggest that deception can arise as an emergent behaviour in LLM-agent systems and that communication between LLM-agents could support sustainability while dealing with risk.
Key facts. No citing papers in the map yet (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 35 of its 80 references that are in the map. First posted on arXiv 26 Jun 2026.
Builds on
35 of 80 references.
Closest ancestors · 15
Same direction, newest first
- 2026Evaluating Collective Behaviour of Hundreds of LLM Agents18 Feb
- 2025Understanding LLM Agent Behaviours via Game Theory: Strategy Recognition, Biases and Multi-Agent Dynamics8 Dec
- 2025The Role of Social Learning and Collective Norm Formation in Fostering Cooperation in LLM Multi-Agent Systems16 Oct
- 2025Emergent Coordination in Multi-Agent Language Models5 Oct
- 2025The Traitors: Deception and Trust in Multi-Agent Language Model Simulations19 May
- 2025Simulating Cooperative Prosocial Behavior with Multi-Agent LLMs: Evidence and Mechanisms for AI Agents to Inform Policy Decisions18 Feb
- 2025Will Systems of LLM Agents Cooperate: An Investigation into a Social Dilemma27 Jan
- 2024On the Principles behind Opinion Dynamics in Multi-Agent Systems of Large Language Models18 Jun
- 2024Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents25 Apr
- 2024Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents19 Feb
- 2024How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis8 Feb
- 2023Do LLM Agents Exhibit Social Behavior?23 Dec
3 more
Other references · 20
- 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 257
- 2023Playing repeated games with Large Language Modelscited by 217
- 2025Agentic Misalignment: How LLMs Could Be Insider Threatscited by 158
- 2023Large Language Models can Strategically Deceive their Users when Put Under Pressurecited by 146
- 2023Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplationcited by 104
- 2024Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?cited by 63
- 2023The Consensus Game: Language Model Generation via Equilibrium Searchcited by 36
- 2024Network Formation and Dynamics Among Multi-LLMscited by 29
- 2024A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarioscited by 23
- 2025Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontierscited by 16
- 2025When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmascited by 15
- 2025When Do Large Language Models Exhibit Unsolicited Deception?cited by 10
8 more
- 2025From the Fluency Fallacy to the Micro-to-Macro Validity Gap: Opportunities and Pitfalls of LLMs in Social Simulationcited by 10
- 2025Do Large Language Model Agents Exhibit a Survival Instinct? An Empirical Study in a Sugarscape-Style Simulationcited by 9
- 2024Cooperative Resilience in Artificial Intelligence Multiagent Systemscited by 8
- 2025Strategic Intelligence in Large Language Models: Evidence from evolutionary Game Theorycited by 7
- 2025LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactionscited by 7
- 2026A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challengescited by 3
- 2026Emergence of Fragility in LLM-based Social Networks: the Case of Moltbookcited by 2
- 2026Who Is Really Playing? Strategic Interaction in AI-Guided Populationscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Trust, Lies, and Long Memories: Emergent Social Dynamics and Reputation in Multi-Round Avalon with LLM Agents
- 2026When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games
- 2026Be Careful Who You Trust: Coordination Dynamics under Corrupted Communication in LLM Multi-Agent Games
- 2026Deception and Communication in Autonomous Multi-Agent Systems: An Experimental Study with Among Us
- 2026The Politician, the Liar, and the Obedient Worker: Emerging Behavior of LLM Agents in Hierarchical Games
- 2026Evolving Deception: When Agents Evolve, Deception Wins
- 2025Do LLMs trust AI regulation? Emerging behaviour of game-theoretic LLM agents
- 2026Trust Between AI Agents: Measuring Formation, Breakage, and Recovery, with Implications for Governing Multi-Agent Systems