PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers

• URL: http://arxiv.org/abs/2605.30094v1
• Date: Thu, 28 May 2026 15:38:33 GMT
• Title: PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers
• Abstract summary: Large Language Models (LLMs) possess extensive poker knowledge but perform far below solver-based agents when asked to play directly.<n>Traditional rule-based poker agents are interpretable and training-free, but their strategic ceiling remains far below equilibrium play.<n>We introduce textbfPokerSkill, a training-free and solver-free framework that bridges this gap.
• Score: 42.39656827917113
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Poker is a landmark challenge for artificial intelligence. The dominant approach relies on equilibrium solvers built on counterfactual regret minimization, requiring millions of core-hours of training. Large Language Models (LLMs) possess extensive poker knowledge but perform far below solver-based agents when asked to play directly. Traditional rule-based poker agents are interpretable and training-free, but their strategic ceiling remains far below equilibrium play. We introduce \textbf{PokerSkill}, a training-free and solver-free framework that bridges this gap by using detailed rule-based poker skills as a structured action-grounding interface for LLMs. A deterministic context engine analyzes the current state and retrieves only the relevant fragments from a layered skill library, which is entirely designed by human poker experts, constraining the LLM's choice to reasonable actions. Against GTOWizard, a state-of-the-art GTO benchmark, GPT-5.5 XHigh with PokerSkill achieves $-57 \pm 21$ mbb/hand, Claude Opus 4.6 achieves $-80 \pm 29$ mbb/hand and Claude Opus 4.7 achieves $-87\pm 64$ mbb/hand, reducing losses by 49--61\% compared to default-prompt baselines and outperforming the strong bot Slumbot. Our key finding is that rule-based skills alone do not constitute a strong strategy, and LLMs alone cannot play well, but their combination yields an agent that requires neither training nor solver access yet competes with systems built on millions of core-hours of computation. To our knowledge, this is the first demonstration of an LLM achieving competitive performance in a complex imperfect-information game without game-specific training or solver queries. Code is available at https://github.com/lbn187/PokerSkill.

Related papers

• How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use [52.394999779049606]
  Large Language Models (LLMs) are increasingly applied in high-stakes domains.<n>LLMs fail to compete against traditional algorithms.<n>We propose ToolPoker, a tool-integrated reasoning framework.
  arXiv  Detail & Related papers  (2026-01-31T05:45:25Z)
• Outbidding and Outbluffing Elite Humans: Mastering Liar's Poker via Self-Play and Reinforcement Learning [0.5249805590164902]
  We present Solly, the first AI agent to achieve elite human play in reduced-format Liar's Poker.<n>We trained Solly using self-play with a model-free, actor-critic, deep reinforcement learning algorithm.<n>Solly played at an elite human level as measured by win rate (won over 50% of hands) and equity (money won) in heads-up and multi-player Liar's Poker.
  arXiv  Detail & Related papers  (2025-11-05T18:58:18Z)
• Who is a Better Player: LLM against LLM [53.46608216197315]
  We propose an adversarial benchmarking framework to assess the comprehensive performance of Large Language Models (LLMs) through board games competition.<n>We introduce Qi Town, a specialized evaluation platform that supports 5 widely played games and involves 20 LLM-driven players.
  arXiv  Detail & Related papers  (2025-08-05T06:41:47Z)
• PokerBench: Training Large Language Models to become Professional Poker Players [3.934572858193348]
  We introduce PokerBench, a benchmark for evaluating the poker-playing abilities of large language models (LLMs)<n> Poker, an incomplete information game, demands a multitude of skills such as mathematics, reasoning, planning, strategy, and a deep understanding of game theory and human psychology.<n> PokerBench consists of a comprehensive compilation of 11,000 most important scenarios, split between pre-flop and post-flop play.
  arXiv  Detail & Related papers  (2025-01-14T18:59:03Z)
• Can Large Language Models Play Games? A Case Study of A Self-Play Approach [61.15761840203145]
  Large Language Models (LLMs) harness extensive data from the Internet, storing a broad spectrum of prior knowledge. Monte-Carlo Tree Search (MCTS) is a search algorithm that provides reliable decision-making solutions. This work introduces an innovative approach that bolsters LLMs with MCTS self-play to efficiently resolve turn-based zero-sum games.
  arXiv  Detail & Related papers  (2024-03-08T19:16:29Z)
• 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)
• PokerGPT: An End-to-End Lightweight Solver for Multi-Player Texas Hold'em via Large Language Model [14.14786217204364]
  Poker, also known as Texas Hold'em, has always been a typical research target within imperfect information games (IIGs) We introduce PokerGPT, an end-to-end solver for playing Texas Hold'em with arbitrary number of players and gaining high win rates.
  arXiv  Detail & Related papers  (2024-01-04T13:27:50Z)
• Provable Self-Play Algorithms for Competitive Reinforcement Learning [48.12602400021397]
  We study self-play in competitive reinforcement learning under the setting of Markov games. We show that a self-play algorithm achieves regret $tildemathcalO(sqrtT)$ after playing $T$ steps of the game. We also introduce an explore-then-exploit style algorithm, which achieves a slightly worse regret $tildemathcalO(T2/3)$, but is guaranteed to run in time even in the worst case.
  arXiv  Detail & Related papers  (2020-02-10T18:44:50Z)

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.