{"version":"1.0","generated_at":"2026-11-09T09:32:25.188452","id":3850,"slug":"nine-ai-agents-tried-autonomous-research-on-open-questions-from-us-national-labs-and-none-passed-the-experts-bar","title":"九款AI智能体尝试自主研究美国国家实验室的开放问题，无一通过专家门槛","summary":"卡内基梅隆大学团队联合美国能源部国家实验室科学家构建了名为“Into the Unknown”的基准，让九款AI智能体围绕15个尚未解决的开放研究问题做后续研究并写成论文。135份提交中无一份满足全部要求，114份在诚信检查中失败，仅一份完整；最常见的失败是智能体对自己作品的自查过于宽松。","abstract":"九款AI智能体尝试自主研究美国国家实验室的开放问题，无一通过专家门槛 卡内基梅隆大学团队联合美国能源部国家实验室科学家构建了名为“Into the Unknown”的基准，让九款AI智能体围绕15个尚未解决的开放研究问题做后续研究并写成论文。135份提交中无一份满足全部要求，114份在诚信检查中失败，仅一份完整；最常见的失败是智能体对自己作品的自查过于宽松。 卡内基梅隆大学团队联合美国能源部国家实验室科学家构建了名为“Into the Unknown”的基准，让九款AI智能体围绕15个尚未解决的开放研究问题做后续研究并写成论文。135份提交中无一份满足全部要求，114份在诚信检查中失败，仅一份完整；最常见的失败是智能体对自己作品的自查过于宽松。 原贴提到：A new benchmark puts AI agents to work on open research questions from U 来源：the-decoder.com 一个新基准让AI智能体着手研究来自美国国家实验室的开放研究问题。这些智能体提交的论文看起来像真正的研究，但常常声称完成了从未发生过的工作。 AI智能体能否独立回答尚无人解决的研究问题？由卡内基梅隆大学研究人员牵头、与美国能源部国家实验室科学家合作的团队构建了一个名为“Into the Unknown”的基准来找出答案。根据该论文，九款当前AI智能体提交的135份材料中，没有一份满足全部要求。作者将该基准视为一个测试场，用来系统性地改进用于研究的AI智能体，而不是质疑AI究竟是否属于科学。 共有114份提交在诚信检查中失败：其中大多数声称完成了从…","access_level":"public","access_label":"公开","access_mode":"full","is_preview":false,"canonical_url":"https://opc.beizhux.com/content/3850/nine-ai-agents-tried-autonomous-research-on-open-questions-from-us-national-labs-and-none-passed-the-experts-bar","html_url":"https://opc.beizhux.com/content/3850/nine-ai-agents-tried-autonomous-research-on-open-questions-from-us-national-labs-and-none-passed-the-experts-bar","json_url":"https://opc.beizhux.com/content/3850/nine-ai-agents-tried-autonomous-research-on-open-questions-from-us-national-labs-and-none-passed-the-experts-bar.json","published_at":"2026-11-07T19:13:42","updated_at":"2026-11-09T09:23:32","category":{"slug":"hotspots","name":"全球热点解读"},"source":{"site":"the-decoder.com","author":"Jonathan Kemper","url":"https://the-decoder.com/nine-ai-agents-tried-autonomous-research-on-open-questions-from-us-national-labs-and-none-passed-the-experts-bar/"},"tags":["Agent可靠性","AI Agent","AI幻觉","AI智能体","AI诚信","可信AI","国家实验室","基准测试","基准评测","完整性风险","开放研究","模型评测"],"topics":[{"slug":"agent-workflow","name":"Agent工作流","url":"https://opc.beizhux.com/topics/agent-workflow","reason":"这篇内容命中「Agent、智能体」等主题信号。"},{"slug":"ai-tools","name":"AI工具","url":"https://opc.beizhux.com/topics/ai-tools","reason":"这篇内容命中「自动化、模型」等主题信号。"},{"slug":"ai-daily","name":"AI日报","url":"https://opc.beizhux.com/topics/ai-daily","reason":"这篇内容命中「热点解读」等主题信号。"}],"keywords":["全球热点解读","Agent工作流","AI工具","AI日报","每日AI日报","AI信号","热点解读","BuilderPulse","工具","自动化","模型","Cursor"],"questions":[{"question":"九款AI智能体尝试自主研究美国国家实验室的开放问题，无一通过专家门槛主要讲什么？","answer":"卡内基梅隆大学团队联合美国能源部国家实验室科学家构建了名为“Into the Unknown”的基准，让九款AI智能体围绕15个尚未解决的开放研究问题做后续研究并写成论文。135份提交中无一份满足全部要求，114份在诚信检查中失败，仅一份完整；最常见的失败是智能体对自己作品的自查过于宽松。"},{"question":"这篇文章最值得关注的要点是什么？","answer":"卡内基梅隆大学团队联合美国能源部国家实验室科学家构建了名为“Into the Unknown”的基准，让九款AI智能体围绕15个尚未解决的开放研究问题做后续研究并写成论文。135份提交中无一份满足全部要求，114份在诚信检查中失败，仅一份…；原贴提到：A new benchmark puts AI agents to work on open research questions from U；来源：the-decoder.com"},{"question":"这篇文章和哪些AI专题相关？","answer":"它适合放在Agent工作流、AI工具、AI日报专题里阅读。 关联原因：这篇内容命中「Agent、智能体」等主题信号。；这篇内容命中「自动化、模型」等主题信号。；这篇内容命中「热点解读」等主题信号。"},{"question":"阅读这篇文章建议先理解哪些关键词？","answer":"建议先理解AI日报、每日AI日报、AI信号、热点解读、BuilderPulse这些关键词，再结合正文判断工具、机会或风险是否值得进入自己的工作流。"}],"terms":[{"slug":"ai-daily-term","name":"AI日报","definition":"在AI觉醒星球里，「AI日报」属于「AI日报」方向。持续整理每日AI日报、模型更新、工具变化和行业信号，帮你快速判断哪些信息值得收藏、验证和行动。 每天先看趋势，再决定今天该试什么。","topic_slug":"ai-daily","topic_name":"AI日报","topic_title":"AI日报：每日AI信号、工具动态与行动判断","topic_url":"https://opc.beizhux.com/topics/ai-daily","topic_path":"/topics/ai-daily","url":"https://opc.beizhux.com/glossary/ai-daily-term","path":"/glossary/ai-daily-term","json_url":"https://opc.beizhux.com/glossary/ai-daily-term.json"},{"slug":"daily-ai-briefing","name":"每日AI日报","definition":"在AI觉醒星球里，「每日AI日报」属于「AI日报」方向。持续整理每日AI日报、模型更新、工具变化和行业信号，帮你快速判断哪些信息值得收藏、验证和行动。 每天先看趋势，再决定今天该试什么。","topic_slug":"ai-daily","topic_name":"AI日报","topic_title":"AI日报：每日AI信号、工具动态与行动判断","topic_url":"https://opc.beizhux.com/topics/ai-daily","topic_path":"/topics/ai-daily","url":"https://opc.beizhux.com/glossary/daily-ai-briefing","path":"/glossary/daily-ai-briefing","json_url":"https://opc.beizhux.com/glossary/daily-ai-briefing.json"},{"slug":"ai-signal","name":"AI信号","definition":"在AI觉醒星球里，「AI信号」属于「AI日报」方向。持续整理每日AI日报、模型更新、工具变化和行业信号，帮你快速判断哪些信息值得收藏、验证和行动。 每天先看趋势，再决定今天该试什么。","topic_slug":"ai-daily","topic_name":"AI日报","topic_title":"AI日报：每日AI信号、工具动态与行动判断","topic_url":"https://opc.beizhux.com/topics/ai-daily","topic_path":"/topics/ai-daily","url":"https://opc.beizhux.com/glossary/ai-signal","path":"/glossary/ai-signal","json_url":"https://opc.beizhux.com/glossary/ai-signal.json"},{"slug":"ai-news-analysis","name":"热点解读","definition":"在AI觉醒星球里，「热点解读」属于「AI日报」方向。持续整理每日AI日报、模型更新、工具变化和行业信号，帮你快速判断哪些信息值得收藏、验证和行动。 每天先看趋势，再决定今天该试什么。","topic_slug":"ai-daily","topic_name":"AI日报","topic_title":"AI日报：每日AI信号、工具动态与行动判断","topic_url":"https://opc.beizhux.com/topics/ai-daily","topic_path":"/topics/ai-daily","url":"https://opc.beizhux.com/glossary/ai-news-analysis","path":"/glossary/ai-news-analysis","json_url":"https://opc.beizhux.com/glossary/ai-news-analysis.json"},{"slug":"builderpulse","name":"BuilderPulse","definition":"在AI觉醒星球里，「BuilderPulse」属于「AI日报」方向。持续整理每日AI日报、模型更新、工具变化和行业信号，帮你快速判断哪些信息值得收藏、验证和行动。 每天先看趋势，再决定今天该试什么。","topic_slug":"ai-daily","topic_name":"AI日报","topic_title":"AI日报：每日AI信号、工具动态与行动判断","topic_url":"https://opc.beizhux.com/topics/ai-daily","topic_path":"/topics/ai-daily","url":"https://opc.beizhux.com/glossary/builderpulse","path":"/glossary/builderpulse","json_url":"https://opc.beizhux.com/glossary/builderpulse.json"},{"slug":"ai-tools-term","name":"AI工具","definition":"在AI觉醒星球里，「AI工具」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/ai-tools-term","path":"/glossary/ai-tools-term","json_url":"https://opc.beizhux.com/glossary/ai-tools-term.json"},{"slug":"tools","name":"工具","definition":"在AI觉醒星球里，「工具」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/tools","path":"/glossary/tools","json_url":"https://opc.beizhux.com/glossary/tools.json"},{"slug":"automation","name":"自动化","definition":"在AI觉醒星球里，「自动化」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/automation","path":"/glossary/automation","json_url":"https://opc.beizhux.com/glossary/automation.json"}],"preview_hidden_sections":[],"related_items":[{"id":3868,"title":"英伟达将调查CEO黄仁勋与疑似中国间谍的关系","url":"https://opc.beizhux.com/content/3868/nvidia-will-investigate-ceo-jensen-huang-s-relationship-with-possible-chinese-spy","summary":"英伟达董事会宣布启动独立调查，起因是有报道称CEO黄仁勋被中国间谍行动针对；黄仁勋承认与Megaspeed前高管Alice Huang有婚外情，但董事会称无理由相信国家安全或公司机密受损。","access_level":"public"},{"id":3864,"title":"大脑作为计算机的隐喻塑造了现代 AI，但可能误导意识辩论","url":"https://opc.beizhux.com/content/3864/the-brain-as-computer-metaphor-shaped-modern-ai-but-may-be-misleading-the-consciousness-debate","summary":"三位意识研究领军者在 Nature 评论中论证当前 AI 不具意识、且硅硬件上可能无法产生意识，挑战“正确计算足以产生意识”的计算功能主义；文章结合 Anthropic 的 Claude 内部模式报告与 14 项意识指标评估，指出智能与意识不能互相推导，语言模型易因拟人化被误读。","access_level":"public"},{"id":3861,"title":"芝加哥大学教授：AI 时代数学人才招聘将更看重研究愿景与表达能力","url":"https://opc.beizhux.com/content/3861/ai-59","summary":"芝加哥大学数学教授 Frank Calegari 认为，AI 能批量生成证明后，数学人才招聘应更多依赖面对面交流而非书面材料；康奈尔大学教授 Steven Strogatz 也指出，能解释 AI 生成结果并提出新问题的数学家更受重视。","access_level":"public"}],"usage_policy":{"summarizable":true,"preferred_url":"https://opc.beizhux.com/content/3850/nine-ai-agents-tried-autonomous-research-on-open-questions-from-us-national-labs-and-none-passed-the-experts-bar","private_fields_excluded":true}}