AutoTrainess：教語言模型自主改進語言模型

摘要

训练语言模型（LMs）仍是一个高度依赖人力的过程，即使前沿语言模型智能体在软件工程及其他长周期任务上变得越来越强大。其中一项核心挑战在于，自主后训练不仅仅是编码问题：它要求智能体反复规划迭代、构建与基准对齐的数据、运行稳定的训练任务、评估检查点，并在长达数小时的交互中保持实验状态。我们提出了AutoTrainess——一种语言模型智能体，它将上述操作公开为一系列智能体-计算机接口，涵盖规划、数据准备、训练、评估和日志记录。AutoTrainess并非让智能体在原始命令行界面环境中以未明确指定的动作空间运作，而是将先前的人类经验外化为显式的工作流程、规则和执行约束，引导智能体实现高效且可靠的训练行为。在PostTrainBench上，AutoTrainess的表现始终优于仅使用命令行界面的基线，使用GPT-5.4（Codex）时平均得分为26.94，而仅命令行界面为23.21。此外，它在不同模型和框架上均具有泛化能力，将DeepSeek-V4-Flash（OpenCode）的得分从12.13提升至19.58。

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.