玩转AI：当前最先进的大语言模型在1977年文本冒险游戏Zork中的表现如何？
Playing With AI: How Do State-Of-The-Art Large Language Models Perform in the 1977 Text-Based Adventure Game Zork?
AI总结：
本文评估了当前最先进的大语言模型在1977年文本冒险游戏Zork中的表现，发现其在问题解决和推理能力上存在显著局限。
摘要：
本文通过评估Zork游戏中的表现，检验了当前大型语言模型（LLMs）的问题解决和推理能力。Zork作为1977年首次发布的文本冒险游戏，其基于对话的结构为评估LLM聊天机器人如何解读自然语言描述并生成适当的操作序列以在游戏中取得成功提供了受控环境。我们测试了领先的专有模型——ChatGPT、Claude和Gemini在最小和详细指示下的表现，通过获得的分数作为主要指标来衡量游戏进度。我们的结果表明，所有测试的模型平均完成度低于10%，即使表现最好的模型（Claude Opus 4.5）也只能达到350分中的约75分。值得注意的是，提供详细的游戏玩家指示没有带来任何改进，也不启用''扩展思考''。对模型推理过程的定性分析揭示了根本性的限制：重复的不成功行动表明无法反思自己的思考，策略的一致性不持久，尽管有对话历史的访问，但未能从之前的尝试中学习。这些发现表明，当前LLMs在文本冒险游戏领域中的元认知能力和问题解决能力存在显著限制，引发了对其推理能力本质和范围的质疑。
英文摘要：
In this positioning paper, we evaluate the problem-solving and reasoning capabilities of contemporary Large Language Models (LLMs) through their performance in Zork, the seminal text-based adventure game first released in 1977. The game's dialogue-based structure provides a controlled environment for assessing how LLM-based chatbots interpret natural language descriptions and generate appropriate action sequences to succeed in the game. We test the performance of leading proprietary models - ChatGPT, Claude, and Gemini - under both minimal and detailed instructions, measuring game progress through achieved scores as the primary metric. Our results reveal that all tested models achieve less than 10% completion on average, with even the best-performing model (Claude Opus 4.5) reaching only approximately 75 out of 350 possible points. Notably, providing detailed game instructions offers no improvement, nor does enabling ''extended thinking''. Qualitative analysis of the models' reasoning processes reveals fundamental limitations: repeated unsuccessful actions suggesting an inability to reflect on one's own thinking, inconsistent persistence of strategies, and failure to learn from previous attempts despite access to conversation history. These findings suggest substantial limitations in current LLMs' metacognitive abilities and problem-solving capabilities within the domain of text-based games, raising questions about the nature and extent of their reasoning capabilities.
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。
