AWorld项目团队投稿 发自 凹非寺 量子位 | 公众号 QbitAI 2025年的IMO，好戏不断。 7月19日，全世界顶尖大模型在2025年的IMO赛场上几乎全军覆没。时隔1天，OpenAI、DeepMind等顶尖实验室就在IMO 2025赛场斩获5/6 题，震惊数学圈。 有意思的是，7月23日——两位来自Harvard和UCLA的学生，用Gemini 2.5 Pro+自研多轮验证框架，在arXiv扔下一篇论文，首次系统性拆 解了「解题+验证」的IMO解题方法论。48小时后，他们开源了完整代码。 来自蚂蚁的多智能体框架AWorld项目团队也加入了这场卷王之争： 7月24日启动，仅仅6小时，采用AWorld智能体框架，复现并开源了DeepMind的5/6道解题结果，并直接给出了可一键运行的多智能体IMO系 统。 果然，大家好奇的点还是跟传统长思维链LangChain等框架有什么不一样。作者给出的回复，核心就是一个词，自我进化。即，多智能体能够 超越单个智能体，能够用于复杂问题协同，以及强化学习的奖励模型等，最终实现AGI。 IMO 2025，把复杂推理模型推向了一种新的高度（尽管还处在实验室阶段，但Dee ...

Core Viewpoint - OpenAI has launched a new "Study Mode" for ChatGPT, designed to enhance learning by guiding users through problem-solving rather than simply providing answers [1][2]. Summary by Sections Introduction of Study Mode - The Study Mode is now available for free, Plus, Pro, and Team users, with ChatGPT Edu users to gain access in the coming weeks [2]. Educational Impact - Leah Belsky, OpenAI's VP of Education, emphasizes that using ChatGPT for teaching can significantly improve student learning outcomes, while merely using it as an "answer machine" may hinder critical thinking [4]. - Approximately one-third of college students are using ChatGPT to assist with their studies, raising concerns among educators and parents about potential academic dishonesty [4]. Learning Mode Features - The Study Mode does not provide direct answers; instead, it poses guiding questions to encourage users to think through problems and summarize concepts in their own words [12][15]. - The design of the Study Mode is a result of collaboration with educators and experts in teaching methodologies, incorporating long-term research in learning science [15]. Interactive Learning - Key features include: - Interactive questioning that promotes active learning through Socratic questioning and self-reflection prompts [16]. - Scaffolding responses that organize information into understandable parts, highlighting key connections between topics [16]. - Knowledge checks through quizzes and open-ended questions, providing personalized feedback to support knowledge retention [17]. Customization and Flexibility - The Study Mode adapts to the user's skill level and past interactions, breaking down complex information into manageable modules while maintaining contextual relevance [18]. - Users can toggle the Study Mode on or off based on their learning objectives [19]. Future Developments - OpenAI views the current Study Mode as an initial step, with plans to refine the model based on real student feedback and to incorporate clearer visual representations for complex concepts [23][24]. - Future improvements may include cross-dialogue goal setting and deeper personalization based on individual student needs [24]. Strategic Intent - OpenAI's CEO, Sam Altman, expresses skepticism about traditional education, suggesting a potential shift in educational paradigms over the next 18 years [26][28]. - This perspective indicates a strategic intent to fundamentally reshape future educational models through AI [28].

Group 1 - The article discusses the concept of "illusory correlation," which refers to the tendency to overestimate the relationship between two variables even when no such relationship exists [1][2] - Illusory correlations are prevalent in decision-making processes, especially in high-pressure environments where individuals rely on mental shortcuts to make quick judgments [2][3] - The article emphasizes the importance of challenging assumptions to uncover hidden cognitive patterns that drive thinking, particularly when making significant decisions [8] Group 2 - The article provides examples of illusory correlations, such as believing that wearing a specific item of clothing leads to success in competitions or that certain days are unlucky for interviews [5][7] - It introduces a contingency table as a method to identify when individuals are most susceptible to illusory correlations, highlighting that the presence of both an outcome and a potential cause is crucial for forming these false associations [3][7] - The article suggests that recognizing and questioning these illusory correlations can lead to better decision-making and a deeper understanding of one's cognitive biases [8]