Large language models increasingly serve as teachers generating training data for smaller students. Prior multi-teacher knowledge distillation methods merge outputs without determining which frontier model teaches best, often relying on an LLM judge biased toward its own outputs. We introduce a compete-then-collaborate framework where four frontier AI teachers (Claude, Codex-GPT, Grok, Gemini) are ranked head-to-head by an execution-based judge (unit tests and stdin-stdout checks) with fairness controls, and then collaborate to build a verifiable curriculum for a student (Qwen2.5-Coder). We report three findings. (1) Under execution verification, all teachers solve standard problems near-perfectly after self-correction (99-100%) due to a saturation effect, but harder competition problems separate them (Gemini 77% > Claude 69% = Codex 69% > Grok 50%); however, the robust student-side results do not depend on teacher ranking. (2) Imitation (SFT) on verified solutions does not improve, and can degrade, an already-competent student at 7B and 32B (e.g., from 76.7% to 72.7% on MBPP-test, and 5.9% to 2.9% on competition problems). (3) Using the same collaborative curriculum as a reinforcement learning with verifiable rewards (RLVR) environment improves the student (from 5.9% to 8.8% peak on competition problems, a +49% relative gain), reversing SFT's direction. The value of AI-teacher collaboration lies not in pooling answers to imitate, but in jointly constructing a verifiable environment where the student learns by doing. We release a reproducible on-prem pipeline (NVIDIA GB10) with framework patches for running GRPO on a bleeding-edge stack.
The Power of Stories: Narrative Priming Shapes How LLM Agents Collaborate and Compete
Department of Data Science and its Applications, German Research Center for Artificial Intelligence (DFKI)(数据科学及其应用系,德国人工智能研究中心(DFKI));Department of Computer Science, University of Kaiserslautern–Landau (RPTU)(计算机科学系,凯撒斯劳滕-兰道大学(RPTU));Department of Language Science and Technology, Saarland University(语言科学与技术系,萨尔兰大学)
本文通过有限重复公共物品博弈实验发现,基于故事的叙事启动能显著影响 LLM 智能体的合作与竞争策略,共同叙事促进合作,而不同叙事使自利倾向智能体占优,对多智能体系统设计和 AI 对齐具有启示。
An NLP-Driven Framework for Curriculum-Labor Market Alignment: Schema-Constrained LLM Extraction, ESCO-Anchored Semantic Matching, and Multi-Dimensional Gap Quantification
United Arab Emirates University(阿联酋大学);Abu Dhabi Polytechnic(阿布扎比理工学院)
CurricuLLM: Designing Personalized and Workforce-Aligned Cybersecurity Curricula Using Fine-Tuned LLMs
Lund University, Department of Electrical;University of Helsinki, Department of Computer Science, Helsinki, Finland;Helsinki Institute for Information Technology, Helsinki, Finland;Karlstad University, Department of Mathematics \& Computer Science, Karlstad, Sweden
Rethinking Generative AI Literacy: An Integrative, Developmental, and Dialectical Framework for K-12 Teacher Education
University of Maryland Baltimore County(马里兰大学巴尔的摩分校);Kent State University(肯特州立大学);Pennsylvania State University(宾夕法尼亚州立大学);The University of Alabama(阿拉巴马大学);George Washington University(乔治华盛顿大学);Pepperdine University(佩珀代因大学);Universiti Malaya(马来亚大学);Begum Rokeya University(贝古姆·罗姬娅大学)
The Impact of Artificial Intelligence on the Evolution of Digital Education: A Comparative Study of OpenAI Text Generation Tools including ChatGPT, Bing Chat, Bard, and Ernie
Department of English literature and language(英语文学与语言系);St.Mary’s University of San Antonio(圣玛丽大学);Foster School of Businesses(商学院);University of Washington(华盛顿大学);Department of Civil and Environmental Engineering(土木与环境工程系);Florida International University(佛罗里达国际大学);Department of Electrical Engineering and Computer Science(电气工程与计算机科学系);Florida Atlantic University(佛罗里达Atlantic大学)