{"version":"1.0","generated_at":"2026-09-27T14:58:45.664801","id":2525,"slug":"world-models-that-ignore-human-beliefs-predict-the-wrong-actions-new-research-shows","title":"新研究：忽略人类信念的世界模型会预测错误行为","summary":"新研究提出'心智世界建模'框架，将信念、意图等心理状态纳入世界模型，提升语言模型对人类行为的预测准确性。","abstract":"新研究：忽略人类信念的世界模型会预测错误行为 新研究提出'心智世界建模'框架，将信念、意图等心理状态纳入世界模型，提升语言模型对人类行为的预测准确性。 新研究提出'心智世界建模'框架，将信念、意图等心理状态纳入世界模型，提升语言模型对人类行为的预测准确性。 原贴提到：Researchers extend AI world models with the \"Mental World Modeling\" fram 来源：the-decoder.com 研究人员将“心智世界建模”框架扩展到 AI 世界模型，以纳入人类信念和意图等心理状态。 在实验中，该方法显著提高了语言模型预测人类行为的准确性。 这是什么信号？ 当前主流的视频生成世界模型（如 Sora、Genie 3、JEPA、Marble）只建模物理层——物体、位置、运动、遮挡，完全忽略人类的信念、意图、社会规范等心理状态。这意味着它们对动态场景的预测只能停留在“物理上可能”，却无法预判“人会怎么做”。新论文提出的“心智世界建模”（MWM）框架，正是为世界模型补上这一关键缺口。 为什么重要？ 因为人类行为主要由内部心理状态驱动，而非纯粹的物理规律。例如，当杯子被移走，物理模型看到的是“杯子不在桌上”，但人却会因不知道杯子被移走而伸手去拿——只有追踪信念的世界模型才能解释这一行为。该研究的参考实现 MENTIS 无需额外训练，通过三步评分（物理合理性、心理一致性、社会适当性）筛选行动，显著提升了对人类行为的预测准确率。这说明心理变量是智能体走向真实世界交互的必需组件。 对谁有价值？ 对服务机器人、医疗助手、协作智能体等需要与人类深…","access_level":"member","access_label":"免费阅读","access_mode":"full","is_preview":false,"canonical_url":"https://opc.beizhux.com/content/2525/world-models-that-ignore-human-beliefs-predict-the-wrong-actions-new-research-shows","html_url":"https://opc.beizhux.com/content/2525/world-models-that-ignore-human-beliefs-predict-the-wrong-actions-new-research-shows","json_url":"https://opc.beizhux.com/content/2525/world-models-that-ignore-human-beliefs-predict-the-wrong-actions-new-research-shows.json","published_at":"2026-08-22T17:00:20","updated_at":"2026-09-27T14:09:12","category":{"slug":"ai-business","name":"AI小生意项目库"},"source":{"site":"the-decoder.com","author":"Jonathan Kemper","url":"https://the-decoder.com/world-models-that-ignore-human-beliefs-predict-the-wrong-actions-new-research-shows/"},"tags":["AI Agent","AI世界模型","AI代理","AI智能体","AI研究","MENTIS","MWM","世界模型","人工智能研究","人机交互","人类行为预测","心智建模"],"topics":[{"slug":"ai-side-business","name":"AI副业","url":"https://opc.beizhux.com/topics/ai-side-business","reason":"这篇内容命中「项目、小生意、变现」等主题信号。"},{"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「模型」等主题信号。"}],"keywords":["AI小生意项目库","AI副业","Agent工作流","AI工具","工具","自动化","模型","Cursor","Claude","Agent","智能体","工作流"],"questions":[{"question":"新研究：忽略人类信念的世界模型会预测错误行为主要讲什么？","answer":"新研究提出'心智世界建模'框架，将信念、意图等心理状态纳入世界模型，提升语言模型对人类行为的预测准确性。"},{"question":"这篇文章最值得关注的要点是什么？","answer":"新研究提出'心智世界建模'框架，将信念、意图等心理状态纳入世界模型，提升语言模型对人类行为的预测准确性。；原贴提到：Researchers extend AI world models with the \"Mental World Modeling\" fram；来源：the-decoder.com"},{"question":"这篇文章和哪些AI专题相关？","answer":"它适合放在AI副业、Agent工作流、AI工具专题里阅读。 关联原因：这篇内容命中「项目、小生意、变现」等主题信号。；这篇内容命中「Agent、智能体」等主题信号。；这篇内容命中「模型」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工具、工具、自动化、模型、Cursor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-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"},{"slug":"ai-model","name":"模型","definition":"在AI觉醒星球里，「模型」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-model","path":"/glossary/ai-model","json_url":"https://opc.beizhux.com/glossary/ai-model.json"},{"slug":"cursor","name":"Cursor","definition":"在AI觉醒星球里，「Cursor」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/cursor","path":"/glossary/cursor","json_url":"https://opc.beizhux.com/glossary/cursor.json"},{"slug":"claude","name":"Claude","definition":"在AI觉醒星球里，「Claude」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/claude","path":"/glossary/claude","json_url":"https://opc.beizhux.com/glossary/claude.json"},{"slug":"agent","name":"Agent","definition":"在AI觉醒星球里，「Agent」属于「Agent工作流」方向。聚合Agent、AI编程、Claude Code、Cursor、工作流自动化等内容，帮助你把智能体能力落到真实任务链路。 把智能体当成任务系统，而不是聊天窗口。","topic_slug":"agent-workflow","topic_name":"Agent工作流","topic_title":"Agent工作流：智能体、AI编程与自动化协作","topic_url":"https://opc.beizhux.com/topics/agent-workflow","topic_path":"/topics/agent-workflow","url":"https://opc.beizhux.com/glossary/agent","path":"/glossary/agent","json_url":"https://opc.beizhux.com/glossary/agent.json"},{"slug":"ai-agent","name":"智能体","definition":"在AI觉醒星球里，「智能体」属于「Agent工作流」方向。聚合Agent、AI编程、Claude Code、Cursor、工作流自动化等内容，帮助你把智能体能力落到真实任务链路。 把智能体当成任务系统，而不是聊天窗口。","topic_slug":"agent-workflow","topic_name":"Agent工作流","topic_title":"Agent工作流：智能体、AI编程与自动化协作","topic_url":"https://opc.beizhux.com/topics/agent-workflow","topic_path":"/topics/agent-workflow","url":"https://opc.beizhux.com/glossary/ai-agent","path":"/glossary/ai-agent","json_url":"https://opc.beizhux.com/glossary/ai-agent.json"}],"preview_hidden_sections":[],"related_items":[{"id":3092,"title":"三分之二的 IT 领导者报告 AI 成果，但很少有人会为此打断 CEO 的假期","url":"https://opc.beizhux.com/content/3092/two-thirds-of-it-leaders-report-ai-results-but-few-would-interrupt-the-ceo-s-vacation-over-them","summary":"AI 泡沫争论的关键问题是 AI 实验室收入能否支撑数据中心建设。Azeem Azhar 分享轶事：约 160 名 IT 副总裁中三分之二有可衡量 AI 成果，但仅约八人认为成果好到能打断 CEO 暑假。企业 AI 回报仍缓慢且难在全经济层面记录，许多公司转向开放权重模型，BCG 调查显示约 70% CEO 有动力美…","access_level":"member"},{"id":3097,"title":"Nvidia 的 SoL-Pi 系统通过优化 harness 将近乎一半的编码 agent token 用量削减","url":"https://opc.beizhux.com/content/3097/nvidia-s-sol-pi-system-cuts-coding-agent-token-usage-nearly-in-half-by-optimizing-the-harness","summary":"Nvidia 论文提出 SoL-Pi，自动优化编码 agent 的控制层 harness。在 EdgeBench 上，token 用量下降 44.7% 到 49%，性能大致持平；按当前 API 价格估算，每小时可节省 4.36 到 13.50 美元。","access_level":"member"},{"id":3084,"title":"使用指标 API 新增拉取请求审查阶段","url":"https://opc.beizhux.com/content/3084/usage-metrics-api-adds-pull-request-review-stages","summary":"GitHub 在企业与组织仓库级 Copilot 使用指标中新增 pull_request_review_times 数组，把 PR 从准备审查到合并拆成三个阶段，分别给出中位数和 P90 耗时，帮助团队定位审查等待发生在哪里。","access_level":"member"}],"usage_policy":{"summarizable":true,"preferred_url":"https://opc.beizhux.com/content/2525/world-models-that-ignore-human-beliefs-predict-the-wrong-actions-new-research-shows","private_fields_excluded":true}}