发表机构
Peargent Labs（Peargent实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出时间感知序列的人类国际象棋AI Otter，结合走法历史编码器与用时控制模块，以更少参数和训练数据超越Maia 2，实现更精准的人类走法预测，相关资源已公开。
AI 中文摘要
Otter是一个拥有1530万参数的人类国际象棋AI，它将对弈建模为时间感知的序列过程，而非孤立处理每个局面，以此预测人类的走法选择。它结合了两种条件信号：（1）走法历史编码器，基于最近20步走法对预测进行条件约束，捕捉开局偏好、局面演变及对局内行为倾向；（2）用时控制模块，根据时钟压力调整预测。Otter在单个T4 GPU上训练了30天，使用了来自Lichess平台1.17亿局快棋的61亿个局面。Otter的走法预测准确率达到Top-1为55.23%、Top-5为90.95%，超越了此前的最先进人类国际象棋模型Maia 2，且参数更少、训练数据更少。在11个Elo等级分区间（从<1100到≥2000）中，准确率在1900-1999区间达到峰值57.38%。这些结果表明，将国际象棋建模为时间感知的序列活动，比仅基于局面的方法能实现更符合人类走法的预测，且使用的模型规模更小。代码、训练好的模型及完整训练日志已公开发布。
英文摘要
Otter is a 15.3M-parameter human chess AI that predicts human move selection by modeling play as a time-aware, sequential process rather than treating each position in isolation. It combines two conditioning signals: (1) a move history encoder that conditions predictions on the last 20 moves, capturing opening preferences, positional drift, and intra-game behavioral tendencies; and (2) a time control module that modulates predictions based on clock pressure. Otter is trained on 6.1 billion positions from 117 million Lichess rapid games over 30 days on a single T4 GPU. Otter achieves 55.23% top-1 and 90.95% top-5 move-prediction accuracy, surpassing the prior state-of-the-art human chess model, Maia 2, with far fewer parameters and less training data. Across 11 Elo brackets (<1100 to >=2000), accuracy peaks at 57.38% in the 1900-1999 bracket. These results show that modeling chess as a time-aware, sequential activity yields more human-accurate move prediction than position-only approaches, using a smaller model. Code, trained models, and complete training logs are publicly released.
