Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy

Large language models are making research production scalable, shifting the bottleneck from producing artifacts to judging claims. We present $\text{textsc}Agon$, a research orchestrator that validates what can be checked inside the workflow and leaves the remaining judgments to human scientists. $\text{textsc}Agon$ is built on six design principles: Prompt Economy, Future-Facing, Minimal Prompts, OmniDisciplinary, Massive Parallelism, and Zero-Code. We ran $\text{textsc}Agon$ across domains for 444 iterations of Prompt Economy loops, using only small starting topics and no human-written experimental code. These deployments demonstrate scalability while exposing new classes of failure. We organize these failures into a taxonomy along severity, fixability, visibility, and capability locus. The taxonomy separates failures the loops can see and fix from those that require human judgment. Together, these results show that $\text{textsc}Agon$ is pushing research toward a new paradigm: machine scales, human steers.