arXiv cs.AI· Qifan Zhang, Yuhan Li, Nuo Chen, Bowen Liu, Xiao Hu, Miao Peng, Chenyi Zi, Lixin Liu, Lydell Huang, Jing Tang, Jia Li·· 2 小时前AI 评分47
Poseidon：从代码仓库规模化构建科学智能体训练环境
POSEIDON: Scaling Training Environments for Scientific Agents from Code Repositories
AI 导读
研究者提出 Poseidon，一个从科学代码仓库自动生成可验证训练环境的流水线，通过 Reproduction、Subflow、Completion、Correction 四类任务分解，在同等仓库预算下提取的环境数量约为此前方法的 10 倍。
正文 · 原文
Authors:Qifan Zhang, Yuhan Li, Nuo Chen, Bowen Liu, Xiao Hu, Miao Peng, Chenyi Zi, Lixin Liu, Lydell Huang, Jing Tang, Jia Li
Abstract:Training environments remain a major bottleneck for agents in data-driven scientific discovery. Existing collections of executable and verifiable training environments are small, and their construction remains difficult to scale. To address this limitation, we introduce Poseidon, an automated pipeline for generating diverse, verifiable training environments from scientific code repositories at scale. From the same repository budget, Poseidon extracts nearly 10 times as many training environments as a prior approach by decomposing scientific workflows into four complementary task types: Reproduction, Subflow, Completion, and Correction, where each type targets a distinct capability for scientific research. A recursive improvement loop further refines failed candidates and recovers otherwise discarded environments. Using Poseidon, we construct Pearl, a collection of 97,659 executable and verifiable environments from 7,110 public repositories spanning 10 scientific disciplines. To the best of our knowledge, Pearl is the largest and most broadly multidisciplinary collection of scientific-agent training environments to date. Qwen3.5 models (9B, 27B, and 35B-A3B) trained on Pearl achieve consistent gains across six challenging scientific-agent benchmarks. Overall, the scale and diversity of Pearl offer opportunities for training scientific discovery agents.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32448 [cs.AI] |
| (or arXiv:2610.32448v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32448 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Qifan Zhang [view email]
[v1]
Fri, 23 Oct 2026 10:14:22 UTC (1,643 KB)
来源：arXiv cs.AI · arxiv.org