Do LLMs Know When to Flip a Coin? Strategic Randomization through Reasoning and Experience

• URL: http://arxiv.org/abs/2506.18928v1
• Date: Sat, 21 Jun 2025 05:26:33 GMT
• Title: Do LLMs Know When to Flip a Coin? Strategic Randomization through Reasoning and Experience
• Abstract summary: Strategic randomization is a key principle in game theory, yet it remains underexplored in large language models (LLMs)<n>We propose a novel zero-sum game inspired by the Tian Ji Horse Race, where the Nash equilibrium corresponds to a maximal entropy strategy.<n>We show that weaker models remain deterministic regardless of prompts, while stronger models exhibit increased randomization under explicit hints.
• Score: 1.7223564681760168
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Strategic randomization is a key principle in game theory, yet it remains underexplored in large language models (LLMs). Prior work often conflates the cognitive decision to randomize with the mechanical generation of randomness, leading to incomplete evaluations. To address this, we propose a novel zero-sum game inspired by the Tian Ji Horse Race, where the Nash equilibrium corresponds to a maximal entropy strategy. The game's complexity masks this property from untrained humans and underdeveloped LLMs. We evaluate five LLMs across prompt styles -- framed, neutral, and hinted -- using competitive multi-tournament gameplay with system-provided random choices, isolating the decision to randomize. Results show that weaker models remain deterministic regardless of prompts, while stronger models exhibit increased randomization under explicit hints. When facing weaker models, strong LLMs adopt deterministic strategies to exploit biases, but converge toward equilibrium play when facing peers. Through win/loss outcomes and Bayes factor analysis, we demonstrate meaningful variation in LLMs' strategic reasoning capabilities, highlighting opportunities for improvement in abstract reasoning and adaptive learning. We make our implementation publicly available at https://github.com/ocelopus/llm-when-to-throw-coin to ensure full reproducibility.

Related papers

• Solver-Guided Reasoning for Mixed-Equilibrium Strategies [38.03807500614725]
  Mixed-Strategy Decision Tree (MDT) articulates the silent optimality of the equilibrium into sparse strategic rules.<n>We instantiate this study on No-Limit Texas Hold'em by querying a solver oracle for over textbf250 million mixed-strategy decisions.
  arXiv  Detail & Related papers  (2026-08-07T03:12:06Z)
• Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning [50.352417879912515]
  Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities.<n>We propose Group Causal Counterfactual Policy Optimization to explicitly train LLMs to learn generalizable reasoning patterns.<n>We then construct token-level advantages from this reward and optimize the policy, encouraging LLMs to favor reasoning patterns that are process-valid and counterfactually robust.
  arXiv  Detail & Related papers  (2026-02-06T08:03:11Z)
• Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies [54.08697738311866]
  Social deduction games like Werewolf combine language, reasoning, and strategy.<n>We curate a high-quality, human-verified multimodal Werewolf dataset containing over 100 hours of video, 32.4M utterance tokens, and 15 rule variants.<n>We propose a novel strategy-alignment evaluation that leverages the winning faction's strategies as ground truth in two stages.
  arXiv  Detail & Related papers  (2025-10-13T13:33:30Z)
• What-If Analysis of Large Language Models: Explore the Game World Using Proactive Thinking [50.72154186522052]
  Large language models (LLMs) excel at processing information reactively but lack the ability to systemically explore hypothetical futures.<n>We propose WiA-LLM, a new paradigm that equips LLMs with proactive thinking capabilities.<n>We validate WiA-LLM in Honor of Kings, a complex multiplayer game environment.
  arXiv  Detail & Related papers  (2025-09-05T04:05:27Z)
• Playing games with Large language models: Randomness and strategy [15.379345372327375]
  Large language models (LLMs) can play games, investigating their capabilities for randomisation and strategic adaptation.<n>We focus on GPT-4o-Mini-2024-08-17 and test two games between LLMs: Rock Paper Scissors (RPS) and games of strategy (Prisoners Dilemma PD)<n>Our research reveals that LLMs appear to develop loss aversion strategies in repeated games, with RPS converging to stalemate conditions while PD shows systematic shifts between cooperative and competitive outcomes based on prompt design.
  arXiv  Detail & Related papers  (2025-03-04T13:04:48Z)
• GAMEBoT: Transparent Assessment of LLM Reasoning in Games [54.49589494014147]
  GAMEBoT is a gaming arena designed for rigorous assessment of Large Language Models.<n>We benchmark 17 prominent LLMs across eight games, encompassing various strategic abilities and game characteristics.<n>Our results suggest that GAMEBoT presents a significant challenge, even when LLMs are provided with detailed CoT prompts.
  arXiv  Detail & Related papers  (2024-12-18T08:32:53Z)
• TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMs [45.12542636218608]
  We propose TMGBench, characterized by comprehensive game type coverage, diverse scenarios and flexible game organization.<n>Specifically, we incorporate all 144 game types summarized by the Robinson-Goforth topology of 2x2 games, constructed as classic games in our benchmark.<n>To provide a sustainable evaluation framework adaptable to increasingly powerful LLMs, we treat the aforementioned games as atomic units.
  arXiv  Detail & Related papers  (2024-10-14T13:15:34Z)
• Are Large Language Models Strategic Decision Makers? A Study of Performance and Bias in Two-Player Non-Zero-Sum Games [56.70628673595041]
  Large Language Models (LLMs) have been increasingly used in real-world settings, yet their strategic decision-making abilities remain largely unexplored. This work investigates the performance and merits of LLMs in canonical game-theoretic two-player non-zero-sum games, Stag Hunt and Prisoner Dilemma. Our structured evaluation of GPT-3.5, GPT-4-Turbo, GPT-4o, and Llama-3-8B shows that these models, when making decisions in these games, are affected by at least one of the following systematic biases.
  arXiv  Detail & Related papers  (2024-07-05T12:30:02Z)
• Large Language Models Playing Mixed Strategy Nash Equilibrium Games [1.060608983034705]
  This paper focuses on the capabilities of Large Language Models to find the Nash equilibrium in games with a mixed strategy Nash equilibrium and no pure strategy Nash equilibrium. The study reveals a significant enhancement in the performance of LLMs when they are equipped with the possibility to run code. It is evident that while LLMs exhibit remarkable proficiency in well-known standard games, their performance dwindles when faced with slight modifications of the same games.
  arXiv  Detail & Related papers  (2024-06-15T09:30:20Z)
• GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations [87.99872683336395]
  Large Language Models (LLMs) are integrated into critical real-world applications. This paper evaluates LLMs' reasoning abilities in competitive environments. We first propose GTBench, a language-driven environment composing 10 widely recognized tasks.
  arXiv  Detail & Related papers  (2024-02-19T18:23:36Z)
• Finding mixed-strategy equilibria of continuous-action games without gradients using randomized policy networks [83.28949556413717]
  We study the problem of computing an approximate Nash equilibrium of continuous-action game without access to gradients. We model players' strategies using artificial neural networks. This paper is the first to solve general continuous-action games with unrestricted mixed strategies and without any gradient information.
  arXiv  Detail & Related papers  (2022-11-29T05:16:41Z)
• Who Leads and Who Follows in Strategic Classification? [82.44386576129295]
  We argue that the order of play in strategic classification is fundamentally determined by the relative frequencies at which the decision-maker and the agents adapt to each other's actions. We show that a decision-maker with the freedom to choose their update frequency can induce learning dynamics that converge to Stackelberg equilibria with either order of play.
  arXiv  Detail & Related papers  (2021-06-23T16:48:46Z)
• Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games [78.65798135008419]
  It remains vastly open how to learn the Stackelberg equilibrium in general-sum games efficiently from samples. This paper initiates the theoretical study of sample-efficient learning of the Stackelberg equilibrium in two-player turn-based general-sum games.
  arXiv  Detail & Related papers  (2021-02-23T05:11:07Z)
• Chaos, Extremism and Optimism: Volume Analysis of Learning in Games [55.24050445142637]
  We present volume analyses of Multiplicative Weights Updates (MWU) and Optimistic Multiplicative Weights Updates (OMWU) in zero-sum as well as coordination games. We show that OMWU contracts volume, providing an alternative understanding for its known convergent behavior. We also prove a no-free-lunch type of theorem, in the sense that when examining coordination games the roles are reversed: OMWU expands volume exponentially fast, whereas MWU contracts.
  arXiv  Detail & Related papers  (2020-05-28T13:47:09Z)
• Randomization matters. How to defend against strong adversarial attacks [17.438104235331085]
  We show that adversarial attacks and defenses form an infinite zero-sum game where classical results do not apply. We show that our defense method considerably outperforms Adversarial Training against state-of-the-art attacks.
  arXiv  Detail & Related papers  (2020-02-26T15:31:31Z)

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.