Humans Are More Diverse: Frontier LLMs Show Extreme Policies in Idealised AI Development Races

• URL: http://arxiv.org/abs/2608.01193v1
• Date: Sun, 02 Aug 2026 12:18:00 GMT
• Title: Humans Are More Diverse: Frontier LLMs Show Extreme Policies in Idealised AI Development Races
• Abstract summary: We study strategic safety behaviour among large language model (LLM) agents in races with two to five players.<n>We first verify the game engine, then test rule recall, state tracking, calculation, and stability.<n>The audit shows that strong rule recall can coexist with weak state tracking and expected-payoff calculation.
• Score: 0.4338724691489186
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: An AI development race creates a multi-agent safety dilemma. Each company can develop slowly and safely, or move faster while taking a risk that may remove its final reward. We use this repeated game to study strategic safety behaviour among large language model (LLM) agents in races with two to five players. However, a valid action does not show that an agent understands the game. We therefore place an audit gate before behavioural interpretation. We first verify the game engine, then test rule recall, state tracking, payoff calculation, and stability under different but equivalent task descriptions. We then compare LLM action sequences with an evolutionary game-theory benchmark and published human data, and explore differences across models, risk conditions, personas, and two- to five-player races. The audit shows that strong rule recall can coexist with weak state tracking and expected-payoff calculation. Providing verified arithmetic and changing the response representation can also change later actions, even when the game rules stay fixed. Across seven tested model endpoints, aggregate rates hide large differences in action sequences, responses to opponents, and responses to race position. Patterns across the tested three- to five-player races are also model-specific rather than a single effect of adding competitors. These results show why multi-agent AI-race simulations need validity checks and trajectory-level analysis before their outputs are described as strategic, human-like, or safety-aware. Our findings are exploratory and apply only to the tested models, prompts, and decoding settings.

Related papers

• Spatial Reasoning in LLM Game Agents: Impact of Causal Context and Multi-Step Planning [56.67877550139192]
  We conduct experiments across varying model scales, reasoning modes, and planning horizons.<n>We introduce a focused GVGAI benchmark consisting of three custom games with five difficulty levels to isolate spatial navigation.<n>Our results show that while larger models with an enabled thinking mode identify their positions more accurately, overall performance in coordinate matching remains limited for smaller models.
  arXiv  Detail & Related papers  (2026-07-22T12:10:45Z)
• MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs [54.81359054218573]
  We introduce Mindgames, a multi-game arena and evaluation platform for large language models (LLMs)<n>Mindgames provides a unified interaction interface, TrueSkill-based rating, and full trajectory logging across four game environments.<n>We analyze 29,571 multi-agent games with turn-level observations, actions, and rewards, together with MG-Ref, a deterministic offline tournament protocol.
  arXiv  Detail & Related papers  (2026-05-28T07:33:47Z)
• 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)
• GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents [76.60994803070436]
  GameWorld is a benchmark for evaluation of Multimodal Large Language Model (MLLM) game agents in browser environments.<n>Two game agent interfaces are studied: (i) computer-use agents that directly emit keyboard and mouse controls, and (ii) generalist multimodal agents that act in a semantic action space.<n>Results across 18 model-interface pairs suggest that even the best performing agent is far from achieving human capabilities on video games.
  arXiv  Detail & Related papers  (2026-04-08T17:49:03Z)
• From Gameplay Traces to Game Mechanics: Causal Induction with Large Language Models [64.43268969806098]
  We investigate Causal Induction: the ability to infer governing laws from observational data.<n>We compare two approaches to VGDL generation: direct code generation from observations, and a two-stage method that first infers a structural causal model (SCM) and then translates it into VGDL.<n>Results show that the SCM-based approach more often produces VGDL descriptions closer to the ground truth than direct generation.
  arXiv  Detail & Related papers  (2026-01-30T08:48:23Z)
• Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents [56.25101378553328]
  We present Game-TARS, a generalist game agent trained with a unified, scalable action space anchored to human-aligned keyboard-mouse inputs.<n>Game-TARS is pre-trained on over 500B tokens with diverse trajectories and multimodal data.<n> Experiments show that Game-TARS achieves about 2 times the success rate over the previous sota model on open-world Minecraft tasks.
  arXiv  Detail & Related papers  (2025-10-27T17:43:51Z)
• LM Fight Arena: Benchmarking Large Multimodal Models via Game Competition [104.81487689011341]
  We introduce LM Fight Arena, a novel framework that evaluates large multimodal models in Mortal Kombat II.<n>Unlike static evaluations, LM Fight Arena provides a fully automated, reproducible, and objective assessment of an LMM's strategic reasoning capabilities.
  arXiv  Detail & Related papers  (2025-10-10T02:19:21Z)
• Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma? [0.1474723404975345]
  We study the cooperative behavior of Llama2 when playing the Iterated Prisoner's Dilemma against random adversaries displaying various levels of hostility. We find that Llama2 tends not to initiate defection but it adopts a cautious approach towards cooperation. In comparison to prior research on human participants, Llama2 exhibits a greater inclination towards cooperative behavior.
  arXiv  Detail & Related papers  (2024-06-19T14:51:14Z)
• Toward Human-AI Alignment in Large-Scale Multi-Player Games [24.784173202415687]
  We analyze extensive human gameplay data from Xbox's Bleeding Edge (100K+ games) We find that while human players exhibit variability in fight-flight and explore-exploit behavior, AI players tend towards uniformity. These stark differences underscore the need for interpretable evaluation, design, and integration of AI in human-aligned applications.
  arXiv  Detail & Related papers  (2024-02-05T22:55:33Z)
• 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)
• Adversarial Online Learning with Variable Plays in the Pursuit-Evasion Game: Theoretical Foundations and Application in Connected and Automated Vehicle Cybersecurity [5.9774834479750805]
  We extend the adversarial/non-stochastic multi-play multi-armed bandit (MPMAB) to the case where the number of arms to play is variable. The work is motivated by the fact that the resources allocated to scan different critical locations in an interconnected transportation system change dynamically over time and depending on the environment.
  arXiv  Detail & Related papers  (2021-10-26T23:09:42Z)

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.