新论文提出 RSI-Craft 流水线，将研究论文转化为可执行的训练环境（含数据集、指标与评测代码），筛选后保留 281 个后训练任务，用前沿模型生成的轨迹微调 Qwen 模型。9B 版本提升 8.74 分；RSI-Dojo-35B-A3B 在 PostTrainBench 上提升 16.87 分达到 29.95，接近 GLM-5.2 与 GPT 5.5。
Great new paper on recursive self-improvement.
Self-improving AI is one of the most discussed ideas right now. This paper explores training a model to run LLM post-training itself.
(bookmark it)
The team built RSI-Craft, a pipeline that turns research papers into executable training environments, including datasets, metrics, and evaluation code. After filtering for reliability and difficulty, 281 post-training tasks remain. Frontier models solved them under an improved harness, and the filtered trajectories were used to fine-tune Qwen models. The 9B version gains 8.74 points.
RSI-Dojo-35B-A3B gains 16.87 points on PostTrainBench and reaches 29.95, similar to GLM-5.2 and GPT 5.5.
https://arxiv.org/abs/2611.03698
Chat with Paper: https://academy.dair.ai/papers/training-llm-agents-to-automate-llm-post-training-with-rsi-dojo-2611.03698
来源：DAIR.AI · x.com