Do next-generation LLM agents inherit the cooperative biases documented in their predecessors, or does scale and provider diversity reshape equilibrium behaviour in competitive multi-agent settings? Willis et al. established a benchmark for this question using evolutionary game theory and the Iterated Prisoner's Dilemma (IPD), finding consistent cooperative biases in ChatGPT-4o and Claude 3.5 Sonnet. We extend this benchmark to four frontier models released in 2025-2026 - Claude Sonnet 4.6, Gemini 2.5 Flash, Gemini 3.1 Pro, and GPT-5.4 Mini - applying the identical protocol across three prompting styles (Default, Prose, Self-Refine) and four population compositions (balanced and biased, with and without noise). Cooperative bias persists across providers (H1): nine of twelve model-prompt combinations favour cooperative equilibria in balanced noiseless conditions. Cross-provider divergence is substantial (H3): Gemini 2.5 Flash reaches up to 77% aggressive equilibria under biased conditions, while GPT-5.4 Mini reaches 70% cooperative equilibria under Self-Refine. Support for aggressive capability parity is partial (H2): Self-Refine raises ICD in all models and Claude Sonnet 4.6 Refine achieves the highest ICD in the dataset (0.913), but Default and Prose prompts show no systematic narrowing. Evidence on noise robustness is directionally positive but not robustly confirmed (H4): with n=500 Moran iterations per condition, average noise sensitivity is approximately 6 percentage points for Claude Sonnet 4.6 versus 13 pp for Claude 3.5 Sonnet, but this cross-study gap is not statistically significant once the predecessor's unreported sampling error is propagated. Provider identity, rather than model generation, is the strongest correlate of equilibrium outcomes; noise remains a universal challenge regardless of model size or vintage.

翻译：下一代LLM智能体会继承其前身所记录的合作偏向，还是规模和提供商的多样性会重塑竞争性多智能体环境中的均衡行为？Willis等人利用演化博弈论和重复囚徒困境博弈（IPD）为此问题建立了基准，发现ChatGPT-4o和Claude 3.5 Sonnet存在一致的合偏向。我们将此基准扩展到2025-2026年发布的四个前沿模型——Claude Sonnet 4.6、Gemini 2.5 Flash、Gemini 3.1 Pro和GPT-5.4 Mini，在三种提示风格（默认、散文、自我优化）和四种群体构成（平衡与偏向，含噪声与无噪声）下应用相同协议。跨提供商的合作偏向持续存在（H1）：在平衡无噪声条件下，十二种模型-提示组合中有九种倾向于合作均衡。跨提供商的差异显著（H3）：在偏向条件下，Gemini 2.5 Flash达到高达77%的侵略性均衡，而GPT-5.4 Mini在自我优化下达到70%的合作均衡。对侵略性能力均等的支持部分成立（H2）：自我优化提高了所有模型的ICD值，Claude Sonnet 4.6自我优化在数据集中达到最高ICD（0.913），但默认和散文提示未显示系统性缩小。关于噪声鲁棒性的证据呈方向性积极但未得到稳健确认（H4）：在每种条件下n=500次莫兰迭代的情况下，Claude Sonnet 4.6的平均噪声敏感度约为6个百分点，而Claude 3.5 Sonnet为13个百分点，但一旦传播其前身未报告的抽样误差后，此跨研究差距在统计上不显著。提供商身份（而非模型代际）是均衡结果的最强相关因素；无论模型规模或年代如何，噪声仍然是一个普遍挑战。