UniMaia：用语言引导国际象棋策略以实现类人玩法
UniMaia: Steering Chess Policies with Language for Human-like Play
AI总结：
提出UniMaia框架，通过参数高效文本编码器和ControlNet风格调节机制，在冻结的Lc0国际象棋策略网络上实现提示条件策略调制，实现语义控制（如开局选择和玩家强度）并保持预训练策略表征，同时构建大规模元数据增强的Lichess数据集和半自动提示生成管道，在多个基准上取得最优或竞争性结果。
摘要：
大型语言模型的最新进展使得自然语言能够作为控制复杂系统的灵活接口，但通常以大规模多模态训练或弱化领域特定归纳偏差为代价。在结构化决策领域（如国际象棋）中，专门的策略网络表现强劲但缺乏语义可控性，而提示条件语言模型更灵活但通常领域基础较弱。我们提出$ extbf{UniMaia}$，一个用于提示条件策略调制的框架，它使用参数高效文本编码器和ControlNet风格的调节机制来适配基于Lc0的冻结国际象棋策略网络。UniMaia能够实现对游戏玩法的语义控制，包括开局选择和玩家强度，同时保留预训练的策略表征。我们进一步引入$ extbf{UniMaia-Aux}$，它结合了辅助时间条件化和行为预测目标。为了支持这项工作，我们构建了一个大规模元数据增强的Lichess数据集，开发了一个半自动提示生成管道，并引入了涵盖提示条件和元数据条件设置的基准。UniMaia在多个提示条件基准上实现了最先进的预期准确率，在通用指令遵循任务上达到了竞争性的最佳着法准确率，同时在人类着法预测基准上与专门的元数据条件方法保持竞争力。UniMaia-Aux进一步提高了多个评估设置下的预期准确率和行为建模，在最佳着法准确率上略有折衷。总体而言，我们的结果表明，无需端到端多模态训练即可实现领域特定策略网络的提示条件控制，同时突出了可控性与预测性能之间的权衡。
英文摘要：
Recent advances in large language models have enabled natural language to serve as a flexible interface for controlling complex systems, but often at the cost of large-scale multimodal training or weakened domain-specific inductive biases. In structured decision-making domains such as chess, specialized policy networks achieve strong performance but lack semantic controllability, while prompt-conditioned language models are more flexible yet typically exhibit weaker domain grounding. We propose $\textbf{UniMaia}$, a framework for prompt-conditioned policy modulation that adapts a frozen Lc0-based chess policy network using a parameter-efficient text encoder and a ControlNet-style conditioning mechanism. UniMaia enables semantic control over gameplay, including opening selection and player strength, while preserving the pretrained policy representations. We further introduce $\textbf{UniMaia-Aux}$, which incorporates auxiliary temporal conditioning and behavioral prediction objectives. To support this work, we construct a large-scale metadata-augmented Lichess dataset, develop a semi-automated prompt-generation pipeline, and introduce benchmarks spanning both prompt-conditioned and metadata-conditioned settings. UniMaia achieves state-of-the-art expected accuracy on several prompt-conditioned benchmarks and competitive top-move accuracy on general instruction-following tasks, while remaining competitive with dedicated metadata-conditioned approaches on human move prediction benchmarks. UniMaia-Aux further improves expected accuracy and behavioral modeling across several evaluation settings, with modest trade-offs in top-move accuracy. Overall, our results demonstrate that prompt-conditioned control of domain-specific policy networks is feasible without end-to-end multimodal training, while highlighting trade-offs between controllability and predictive performance.
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。
