Markdown version: https://ai.hiina.space/reports/agent-comic-and-manga-studios/07-lessons-transfer-to-manim-and-explainers-almost.md · index

Index of everything on this site: https://ai.hiina.space/index.md

Agent comic studios exist; the reader loop doesn't: 7. Lessons transfer to Manim and explainers almost one-to-one

• Section 7 of 10 of the report "Agent comic studios exist; the reader loop doesn't" by Hiina (v1, updated 2026-10-27)
• Report overview and contents: https://ai.hiina.space/reports/agent-comic-and-manga-studios.md
• Previous: https://ai.hiina.space/reports/agent-comic-and-manga-studios/06-a-six-page-pilot-costs-tens-of.md
• Next: https://ai.hiina.space/reports/agent-comic-and-manga-studios/08-which-gaps-are-real.md

7. Lessons transfer to Manim and explainers almost one-to-one

The comic studio shares one structure with agent-built Manim animations and explainer sites: a programmatic geometry layer (panel frames and balloons; Manim scenes; DOM layout) wrapped around a content layer that is hard to verify. The adjacent evidence points in one direction. Code2Video lost about 41 points when the planner was removed, against 6.5 (aesthetics) to 21 (quiz) points for the critic (Code2Video). OmniManim argues that layout defects appear only after rendering. It gets its biggest gains from a vision agent that predicts bounding boxes into shared scene state, with CV diagnostics routing each fix to the right agent: removing that agent dropped the overlap score from 0.763 to 0.491 (OmniManim). PhysicsSolutionAgent's single VLM screenshot critique gained little, and the VLM sometimes misread frames (PSA). PosterAgent's loop got worse with a weaker VLM (PosterAgent). Four things carry across directly. Put effort into the spec artifact. Key every element to a stable ID with anchors so critique is actionable. Run deterministic overlap and overflow checks before any VLM. Use a comprehension quiz from a blind reader as the headline metric.

Comics are the better first testbed for a specific reason: a still page is fully in distribution for a VLM, while video critique has to infer motion from sampled frames, a limitation PSA calls out. Whatever is learned about judge calibration, cross-family critique and sketch-as-spec on comics is cheap to measure. It then carries to explainer sites almost unchanged, since those are also static renders plus DOM geometry, and to Manim, with the motion caveat.

Text licensed CC BY 4.0 (attribution: Hiina, ai.hiina.space). Source: https://github.com/hiinaspace/ai-hiina-space