让大模型自动训练自己，减少人工干预。
AutoTrainess: Teaching Language Models to Improve Language Models Autonomously
- 设计可复用的训练流程框架，引导大模型自主规划与执行
- 在基准测试中表现优于纯命令行基线，最高提升40%
- 适用于多种模型和训练场景，支持跨模型泛化
训练语言模型仍高度依赖人工，即使前沿语言模型代理已能胜任软件工程等复杂任务。核心挑战在于自主后训练不仅是编程问题，还需反复规划迭代、构建对齐基准的数据、运行稳定训练任务、评估检查点，并在长时间交互中保持实验状态。我们提出 AutoTrainess，一个将规划、数据准备、训练、评估和日志记录等操作封装为明确接口的模型代理。通过将人类经验转化为显式的工作流、规则和执行约束，避免代理在原始命令行环境中因动作空间模糊而失效。在 PostTrainBench 上，AutoTrainess 使用 GPT-5.4（Codex）获得 26.94 的平均得分，优于纯命令行基线的 23.21；同时在 DeepSeek-V4-Flash（OpenCode）上从 12.13 提升至 19.58，展现良好泛化能力。
原文摘要 · Abstract (English)
Training language models (LMs) remains a highly human-intensive process, even as frontier language model agents become increasingly capable at software engineering and other long-horizon tasks. A central challenge is that autonomous post-training is not just a coding problem: it requires the agent to repeatedly plan iterations, construct benchmark-aligned data, run stable training jobs, evaluate checkpoints, and preserve experiment state across many hours of interaction. We present AutoTrainess, a LM agent that exposes these operations as a repository of agent-computer interfaces for planning, data preparation, training, evaluation, and logging. Rather than leaving the agent to operate in a raw CLI environment with an underspecified action space, AutoTrainess externalizes prior human experience as explicit workflows, rules, and execution constraints that guide the agent toward effective and reliable training behavior. On PostTrainBench, AutoTrainess consistently outperforms CLI-only baselines, achieving 26.94 average score with GPT-5.4 (Codex) versus 23.21 for CLI-only. It also generalizes across models and harnesses, improving DeepSeek-V4-Flash (OpenCode) from 12.13 to 19.58.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。