arXiv cs.AI· Youran Sun, Xingyu Ren, Chugang Yi, Jiaxuan Guo, Kejia Zhang, Jianda Du, Haizhao Yang·· 3 小时前AI 评分48
Agon：基于 Prompt Economy 的自主大规模全学科研究系统
Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy
AI 导读
研究者提出 Agon，一个用于探索自动化研究极限的研究编排系统，其设计基于 Prompt Economy、Future-Facing、Minimal Prompts、OmniDisciplinary、Massive Parallelism 和 Zero-Code 六项原则。
正文 · 原文
Abstract:Large language models are making research scalable. We present \textsc{Agon}, a research orchestrator designed to probe the limits of automated research. \textsc{Agon} is built on six design principles: Prompt Economy, Future-Facing, Minimal Prompts, OmniDisciplinary, Massive Parallelism, and Zero-Code. We deployed \textsc{Agon} across domains using only brief topic descriptions as starting points and no human-written code. These deployments demonstrate scalability but also reveal previously unseen classes of failure that are difficult to address through prompt engineering. We organize these failures into a taxonomy along four dimensions: severity, fixability, visibility, and capability locus. Together, these results show that \textsc{Agon} is pushing research towards a new paradigm: machines scale, humans steer. Our code is publicly available at \href{this https URL}{this GitHub repository}.
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2606.24177 [cs.SE] |
| (or arXiv:2606.24177v2 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2606.24177 arXiv-issued DOI via DataCite |
Submission history
From: Youran Sun [view email]
[v1]
Tue, 23 Jun 2026 05:57:09 UTC (368 KB)
[v2]
Tue, 10 Nov 2026 20:24:48 UTC (367 KB)
来源：arXiv cs.AI · arxiv.org