TAG
#mixed-initiative
0 reviews · 3 essays
Related essays
Endrovski et al.: The people using level generation least are the ones who build levels — Fukai Reads
A paper by Bojan Endrovski, Joris Dormans and Rafael Bidarra on procedural level generation tools. Surveying 120 game developers, they found artists use level generation far more than designers (mean usage 0.58 vs 0.33), and that what developers want from AI is creative control over the final output (73.3%), not automation.
Geheeb et al.: Let an LLM Poke at Your Game Design Pillars — Fukai Reads
A paper on game design pillars and LLMs by Julian Geheeb and colleagues at the Technical University of Munich. Pillars are heavily used in industry but almost unexamined academically; the paper gives them a formal definition and quality criteria, then hands structural checking, contradiction detection and feature evaluation to an LLM in a prototype called SPINE. A 42-hour game jam and interviews with four developers produce a consistent picture: useful at the moment of putting a pillar into words, thinning with each rewrite iteration, and unable to recognise deliberate juxtaposition when flagging contradictions. Peer-reviewed at FDG '26.
Luo et al.: How AI Delivers Help Matters as Much as the Help Itself — Fukai Reads
A paper by Luo et al. (UC Santa Barbara) on how a mixed-initiative AI delivers help. Using Rush Hour puzzles, they compare on-demand (Button) help with inactivity-triggered (Timer) help, and show that although task performance is nearly identical, the Timer mode earns more positive perceptions of the AI. Accepted to IUI '26.
