Poker Arena: 大型语言模型中策略推理与记忆的多轴剖析
Poker Arena: Multi-Axis Profiling of Strategic Reasoning and Memory in LLMs
AI总结：
提出Poker Arena平台，通过三层记忆架构和九轴认知剖面分解策略推理，揭示标量排行榜系统性误排模型能力结构。
摘要：
不确定性下的策略推理支撑着谈判、金融和政策中的关键决策，但现有的游戏基准将异质推理维度压缩为单一标量，导致前沿LLM的能力结构未被审视。我们引入Poker Arena，一个无限注德州扑克锦标赛平台，该平台将三层记忆架构（手牌内、会话内和跨会话）与九轴认知剖面相结合，将策略推理分解为可解释的维度，如下注规模校准和位置意识。我们在50个会话（每个会话1000手牌）和受控记忆消融实验中评估了七个前沿模型；锦标赛筹码和聚合轴得分对模型进行了不同排序：Claude Opus 4.6赢得+15,730筹码和14次第一名，但在平均轴得分上仅排名第五（共七个），而持久记忆对某些模型有帮助，对另一些则有损害。这些发现表明，多轴评估揭示了标量排行榜系统性误排的能力结构，其中跨维度一致性优于任何单一维度的峰值性能。
英文摘要：
Strategic reasoning under uncertainty underpins consequential decisions in negotiation, finance, and policy, but prevailing game-play benchmarks collapse heterogeneous reasoning dimensions into a single scalar, leaving the capability structure of frontier LLMs unexamined. We introduce Poker Arena, a no-limit Texas Hold'em tournament platform that couples a three-layer memory architecture (within-hand, session, and cross-session) with a nine-axis cognitive profile decomposing strategic reasoning into interpretable dimensions such as bet-sizing calibration and positional awareness. We evaluate seven frontier models across 50 sessions of 1,000 hands and a controlled memory ablation; tournament chips and aggregate axis score order the field differently: Claude Opus 4.6 wins +$15,730 chips with 14 first-place finishes, yet ranks only fifth of seven on mean axis score, while persistent memory helps some models and hurts others. These findings show that multi-axis evaluation surfaces capability structure that scalar leaderboards systematically misrank, with cross-dimensional consistency outweighing peak performance on any single axis.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
