A Unified Arena for LLM Agents across Diverse Eurogame· 跨多款欧洲桌游的 LLM 代理统一评估
Interactive environments offer a practical way to evaluate large language model (LLM) agents, and competitive games extend this evaluation to decisions shaped by competing goals and other agents' choices. Yet existing evaluations confined to individual games or execution frameworks leave unclear which competitive advantages persist across settings. We introduce DECE (Diverse Eurogame Competitive Environments), a unified arena spanning ten Eurogames with shared interfaces and evaluation protocols. These games combine lasting strategic commitments, competition over shared resources, and multiple routes to victory. Our primary study evaluates 12 model-harness configurations, spanning nine models and four execution harnesses, in 480 three-player matches across ten games. The main and supplemen
介绍 DECE，跨多款欧洲桌游统一评估 LLM 代理的框架。
- 核心方法
- 构建 DECE，一个包含十款欧洲桌游的统一评估环境，具有共享接口和评估协议，用于测试 LLM 代理在复杂竞争环境中的表现。
- 适合谁读
- 研究者、工程师、桌游爱好者
- 要解决的问题
- 现有 LLM 代理评估方法局限于单一游戏或执行框架，无法清晰展示跨设置的竞争优势。
- 关键实验
- 12 种模型配置在 480 场三玩家比赛中进行了评估，涵盖九种模型和四种执行框架。
- 主要贡献
- 提供了一个统一的评估框架，能够测试 LLM 代理在多种游戏中的一致性和适应性。
- 意义与局限
- 有助于理解 LLM 代理在不同游戏中的通用性和局限性，促进模型在复杂多变环境中的改进和发展。