风险评测 · 评测基准

PostTrainBench: Can LLM Agents Automate LLM Post-Training?

NUWA 研究解读 · 独立复核待完成

首次发表: 2026-03-09来源核验: 2026-10-25

原始来源 ↗引用本记录 ↓自主性 →

NUWA Research Note

研究问题研究设计与假设来源发现 NUWA 解读局限与相反证据研究与决策意义机构与角色原始资源

模型辅助整理 · 选读原始全文或官方文章中的相关章节；尚未完成逐章节审计。

研究速读

NUWA 解读：选定后训练增益不证明通用自主AI研究。

研究问题

编程智能体能否通过后训练自主改善给定基础模型？

研究设计与假设

四种小基础模型分别配目标基准，每次限单H100十小时，以保留集评价提交检查点。

来源发现

最佳智能体平均23.2%，基础7.5%，官方指令模型51.1%。

个别模型任务配对可超过官方版本。

NUWA 解读

NUWA 解读：选定后训练增益不证明通用自主AI研究。

局限与相反证据

单任务优化、有限算力和前沿智能体仅三次运行限制外推及方差估计，污染判断可能出错。

研究与决策意义

模型建议：表现增益旁保留目标任务与检查点完整性审查。

精确来源位置

PostTrainBench : Can LLM Agents Automate LLM Post-Training? · AbstractSelected original resource https://arxiv.org/html/2603.08640; sha256:09f5be78dc2b8f33ac7a82fc692485521fd9442d75cca2bd6d3aad76d727d70c; archived source capture; exact capture time not independently established
PostTrainBench : Can LLM Agents Automate LLM Post-Training? · §1 Introduction: Our benchmarkSelected original resource https://arxiv.org/html/2603.08640; sha256:09f5be78dc2b8f33ac7a82fc692485521fd9442d75cca2bd6d3aad76d727d70c; archived source capture; exact capture time not independently established
PostTrainBench : Can LLM Agents Automate LLM Post-Training? · §3.1 Main ResultsSelected original resource https://arxiv.org/html/2603.08640; sha256:09f5be78dc2b8f33ac7a82fc692485521fd9442d75cca2bd6d3aad76d727d70c; archived source capture; exact capture time not independently established
PostTrainBench : Can LLM Agents Automate LLM Post-Training? · §7 Discussion: LimitationsSelected original resource https://arxiv.org/html/2603.08640; sha256:09f5be78dc2b8f33ac7a82fc692485521fd9442d75cca2bd6d3aad76d727d70c; archived source capture; exact capture time not independently established

来源核查、数据提取、编辑批准与实验复现分别记录。方法说明 →

机构与角色

研究机构 ELLIS Institute Tübingen 马克斯·普朗克智能系统研究所蒂宾根大学 Thoughtful Lab

作者 (7)

Ben Rank · Hardik Bhatnagar · Ameya Prabhu · Shira Eisenberg · Karina Nguyen · Matthias Bethge · Maksym Andriushchenko

评测协议

PostTrainBench and OpenAI PostTrainBench Lite →

引用与复用

引用研究发现时请引用原始出版物；引用 NUWA 的整理与解释时，单独引用本站记录及对应快照。

BibTeX ↓RIS ↓记录与来源元数据 · JSON ↓阅读覆盖 · JSON 提交更正

原始出版物 · BibTeX

@misc{posttrainbench,
  title = {PostTrainBench: Can LLM Agents Automate LLM Post-Training?},
  url = {https://arxiv.org/abs/2603.08640},
  author = {Ben Rank and Hardik Bhatnagar and Ameya Prabhu and Shira Eisenberg and Karina Nguyen and Matthias Bethge and Maksym Andriushchenko},
  year = {2026},
  date = {2026-03-09},
  version = {arXiv:2603.08640v2},
  note = {arXiv:2603.08640v2}
}

NUWA 记录 · BibTeX

@misc{posttrainbench-nuwa,
  title = {PostTrainBench: Can LLM Agents Automate LLM Post-Training? — NUWA research record},
  url = {https://whitzard.tech/nuwa/whitzard-index/work/posttrainbench/},
  version = {2026-10-29.1},
  organization = {NUWA Frontier AI Safety Lab},
  howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--posttrainbench.json},
  note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--posttrainbench.json.}
}

证据快照 2026-10-29.1 · 索引更新 · RSS

参考文献

[1] Ben Rank ∗, Hardik Bhatnagar ∗ 等. PostTrainBench: Can LLM Agents Automate LLM Post-Training?. 2026-03-09. v2 [arXiv]; Author affiliations on the original paper title page; Abstract; §1 Introduction: Our benchmark