SpireBench：用《杀戮尖塔》评估智能体长时程策略能力
原标题：SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire
AI 摘要
研究者提出 SpireBench，一个基于商业卡牌游戏《杀戮尖塔》的长时程智能体基准，让模型在最高难度下完成全部56层决策。对20个LLM的测试显示，前沿模型能击败启发式基线和普通人类玩家，但远落后于专家，且随游戏进程拉长差距扩大。通过全游戏术语重命名消融，发现部分表现依赖对游戏的先验知识；跨局记忆机制未能提升表现，因为17%的记忆是错误且过度保守。
正文节选
SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire Abstract Agentic large language models now tackle complex tasks, yet strategic reasoning over long horizons is under-studied: most agentic benchmarks are short and episodic, and performance on long tasks is hard to dissect into stored knowledge, reasoning and luck. We introduce SpireBench, in which models play the complete commercial deck-builder Slay the Spire (StS), where early decisions decide long-term s