Paper
Machinagogy: Experiments in Staging Teaching Dramas with LLMs
Authors
Liam Magee
Abstract
This paper describes an AI tutoring system built upon two psycho-social theoretic constructs: Hegelian recognition and Freudian psychodynamics. Two related interventions are proposed: recognition-enhanced prompts that instruct an AI tutor to treat the learner as an autonomous subject, and a multi-agent ego/superego architecture where an internal critic reviews tutor output. The paper also describes the nature of the human/machine relationship involved in this research itself, employing a reflexive methodology: Claude Code (Opus 4.5/4.6) builds, evaluates, and documents the AI tutor by authoring a companion scientific paper - a process termed "vibe scholarship" - in conjunction with human prompting and suggestion, which is itself documented and analyzed. The companion paper, included as appendix, reports a factorial evaluation across three generation models (DeepSeek V3.2, Haiku 4.5, Gemini Flash 3.0), finding recognition-enhanced prompts produce large, model-independent improvements (d=1.34-1.92) through a calibration mechanism that raises the floor of tutor performance. This result, significant in itself, is combined with the qualitative reflections in this paper to consider impacts of AI on the delicate dynamics of student / teacher and assistant / researcher relations.
Metadata
Related papers
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jian... • 2026-03-30
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or • 2026-03-30
Graphilosophy: Graph-Based Digital Humanities Computing with The Four Books
Minh-Thu Do, Quynh-Chau Le-Tran, Duc-Duy Nguyen-Mai, Thien-Trang Nguyen, Khan... • 2026-03-30
ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Anuj Diwan, Eunsol Choi, David Harwath • 2026-03-30
RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems
Oliver Aleksander Larsen, Mahyar T. Moghaddam • 2026-03-30
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.10450v1</id>\n <title>Machinagogy: Experiments in Staging Teaching Dramas with LLMs</title>\n <updated>2026-03-11T06:07:40Z</updated>\n <link href='https://arxiv.org/abs/2603.10450v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.10450v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>This paper describes an AI tutoring system built upon two psycho-social theoretic constructs: Hegelian recognition and Freudian psychodynamics. Two related interventions are proposed: recognition-enhanced prompts that instruct an AI tutor to treat the learner as an autonomous subject, and a multi-agent ego/superego architecture where an internal critic reviews tutor output. The paper also describes the nature of the human/machine relationship involved in this research itself, employing a reflexive methodology: Claude Code (Opus 4.5/4.6) builds, evaluates, and documents the AI tutor by authoring a companion scientific paper - a process termed \"vibe scholarship\" - in conjunction with human prompting and suggestion, which is itself documented and analyzed. The companion paper, included as appendix, reports a factorial evaluation across three generation models (DeepSeek V3.2, Haiku 4.5, Gemini Flash 3.0), finding recognition-enhanced prompts produce large, model-independent improvements (d=1.34-1.92) through a calibration mechanism that raises the floor of tutor performance. This result, significant in itself, is combined with the qualitative reflections in this paper to consider impacts of AI on the delicate dynamics of student / teacher and assistant / researcher relations.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CY'/>\n <published>2026-03-11T06:07:40Z</published>\n <arxiv:comment>15 pages, 1 figure; plus 135-page automated companion paper (authored by Claude Code) included as appendix with 18 figures and 30+ tables reporting factorial evaluation across three LLM families</arxiv:comment>\n <arxiv:primary_category term='cs.CY'/>\n <author>\n <name>Liam Magee</name>\n </author>\n </entry>"
}