RSI-Craft 论文探索让模型自主完成 LLM 后训练
一篇关于递归自我改进的论文：他们把论文变成可执行训练环境，微调后的 Qwen 35B 在 PostTrainBench 上追平了 GLM-5.2。
论文团队构建了 RSI-Craft 流水线，将研究论文转化为可执行的训练环境，包含数据集、指标和评测代码。经过可靠性和难度过滤后保留 281 个后训练任务，前沿模型在改进的 harness 下解决这些任务。过滤后的轨迹用于微调 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 和 GPT 5.5 的水平。
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://t.co/wOTXJwHPzm
Chat with Paper: https://t.co/oKjJdi8r40
