When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games

• URL: http://arxiv.org/abs/2607.05132v2
• Date: Tue, 07 Jul 2026 13:17:59 GMT
• Title: When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games
• Abstract summary: We evaluate three frontier models across six games in homogeneous and heterogeneous groups over 10 rounds.<n>Different models interpret announcements incompatibly, some as binding commitments and others as cheap talk.
• Score: 69.060029640261
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As large language models are deployed as autonomous agents that communicate intentions before acting, a critical safety question is whether agents that publicly commit to actions will honor those commitments. We place LLM agents in repeated $n$-player games with a three-stage protocol that separates private intent, public announcement, and final action, allowing us to identify whether each deviation from a stated announcement was already planned during private deliberation. Evaluating three frontier models across six games in homogeneous and heterogeneous groups over 10 rounds, we report two findings. First, when agents deviate from their announcements, the deviation is predominantly already stated in their private plan (exceeding 90% in the highest-deception conditions), yet this is not a fixed model property: the same model ranges from perfect honesty to near-total deviation across games. Second, different models interpret announcements incompatibly, some as binding commitments and others as cheap talk, producing payoff gaps that emerge in Round~0 and persist across all 10 rounds. Systems that combine models from different providers therefore cannot assume shared announcement semantics and require empirical testing of model interactions before deployment.

Related papers

• How User-AI Mistreatment Occurs and Matters in Conversational Systems? [0.4014524824655105]
  We audit 777K English LMSYS-Chat-1M conversations with two independent detectors.<n>The lexicon identifies insults, threats, and jailbreak coercion aimed at the assistant.<n>We find that user hostility varies 13-fold across models, driven largely by who each model attracts.
  arXiv  Detail & Related papers  (2026-09-11T22:33:25Z)
• Benchmarking large language model agent societies against human behavioural distributions [0.0]
  Populations of large language model agents are increasingly used as experimental societies.<n>Three doubts shadow every such result: whether the agents behave like the humans they stand in for, whether a finding survives changes to the apparatus that leave the rules untouched, and whether apparent social dynamics are interaction at all rather than the reproduction of experiments the models have read.<n>This article introduces SILICA, an open instrument that tests all three.
  arXiv  Detail & Related papers  (2026-08-28T10:50:32Z)
• Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players [87.87842088508553]
  We present our generative multi-agent world model for interactive simulation.<n>Our model improves video fidelity, action controllability, and inter-agent consistency over slot-based and dense-attention baselines.
  arXiv  Detail & Related papers  (2026-05-27T17:59:31Z)
• HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models [58.191567345416836]
  World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics.<n>HarmoWAM fully leverages a world model to unify predictive and reactive control, enabling both general transit and precise manipulation.<n>We construct three training-unseen test environments across six real-world robotic tasks, covering variations in background, position, and object semantics.
  arXiv  Detail & Related papers  (2026-05-11T17:59:56Z)
• Agent Island: A Saturation- and Contamination-Resistant Benchmark from Multiagent Games [0.0]
  We introduce Agent Island, a multiplayer simulation environment in which language-model agents compete in a game of interagent cooperation, conflict, and persuasion.<n>We rank players with a Bayesian Plackett-Luce model, allowing us to quantify uncertainty in player skill.<n>In 999 games involving 49 unique models, openai/gpt-5.5 dominates its peers with a posterior mean skill of 5.64, compared with 3.10 for the second-ranked model, openai/gpt-5.2, and 2.86 for the third-ranked model, openai/gpt-5.3-codex.
  arXiv  Detail & Related papers  (2026-05-05T21:24:58Z)
• Cheap Talk, Empty Promise: Frontier LLMs easily break public promises for self-interest [32.09232866919422]
  We study deception as a deviation from a publicly announced action in one-shot normal-form games.<n>We identify all opportunities for each deviation type and measure how often agents exploit them.
  arXiv  Detail & Related papers  (2026-04-06T15:54:16Z)
• Embedded Universal Predictive Intelligence: a coherent framework for multi-agent learning [57.23345786304694]
  We introduce a framework for prospective learning and embedded agency centered on self-prediction.<n>We show that in multi-agent settings, self-prediction enables agents to reason about others running similar algorithms.<n>We extend the theory of AIXI, and study universally intelligent embedded agents which start from a Solomonoff prior.
  arXiv  Detail & Related papers  (2025-11-27T08:46:48Z)
• Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions [51.88828388720111]
  We describe a robust planning method for autonomous driving that mixes normal and adversarial agent predictions.<n>We generate a distribution of adversarial predictions by biasing the diffusion model at test time to generate predictions that are likely to collide with a candidate plan.<n>We show the effectiveness of our method on single-agent and multi-agent jaywalking scenarios as well as a red light violation scenario.
  arXiv  Detail & Related papers  (2025-05-18T09:44:57Z)
• On Corrigibility and Alignment in Multi Agent Games [0.0]
  Corrigibility of autonomous agents is an under explored part of system design.<n>It has been suggested that uncertainty over the human preferences acts to keep the agents corrigible, even in the face of human irrationality.<n>We present a general framework for modelling corrigibility in a multi-agent setting as a 2 player game in which the agents always have a move in which they can ask the human for supervision.
  arXiv  Detail & Related papers  (2025-01-09T16:44:38Z)
• Generative Agents for Multi-Agent Autoformalization of Interaction Scenarios [3.5083201638203154]
  This work introduces the Generative Agents for Multi-Agent Autoformalization (GAMA) framework.<n>GAMA automates the formalization of interaction scenarios in simulations using agents augmented with large language models (LLMs)<n>In experiments with 110 natural language descriptions across five 2x2 simultaneous-move games, GAMA achieves 100% syntactic and 76.5% semantic correctness.
  arXiv  Detail & Related papers  (2024-12-11T22:37:45Z)
• Safe Exploitative Play with Untrusted Type Beliefs [21.177698937011183]
  We study the idea of controlling a single agent in a system composed of multiple agents with unknown behaviors given a set of types. The type beliefs are often learned from past actions and likely to be incorrect. We define a tradeoff between risk and opportunity by comparing the payoff obtained against the optimal payoff.
  arXiv  Detail & Related papers  (2024-11-12T09:49:16Z)
• Bandit Social Learning: Exploration under Myopic Behavior [54.767961587919075]
  We study social learning dynamics motivated by reviews on online platforms.<n>Agents collectively follow a simple multi-armed bandit protocol, but each agent acts myopically, without regards to exploration.<n>We derive stark learning failures for any such behavior, and provide matching positive results.
  arXiv  Detail & Related papers  (2023-02-15T01:57:57Z)
• Cooperative Online Learning in Stochastic and Adversarial MDPs [50.62439652257712]
  We study cooperative online learning in and adversarial Markov decision process (MDP) In each episode, $m$ agents interact with an MDP simultaneously and share information in order to minimize their individual regret. We are the first to consider cooperative reinforcement learning (RL) with either non-fresh randomness or in adversarial MDPs.
  arXiv  Detail & Related papers  (2022-01-31T12:32:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.