长上下文 RL 训练的数据构建和奖励设计一直是个难题，GoLongRL 提供了开源数据集和优化方法，做长上下文模型训练的团队可以直接复用，省去大量数据构造工作。
GoLongRL 是一个完全开源的长上下文强化学习训练方案，包含 23K 样本的数据集、完整构建流程和训练代码。该方案基于长上下文能力分类法，覆盖 9 种任务类型，每个任务配有自然评估指标，数据来源包括书籍、学术论文和多轮对话等真实文档。在相同 GRPO 设置下，GoLongRL 数据集优于闭源的 QwenLong-L1.5 数据集，且 Qwen3-30B-A3B 模型在长上下文任务上表现接近 DeepSeek-R1-0528 和 Qwen3-235B-A22B。此外，论文提出 TMN-Reweight 方法，通过任务级均值归一化和难度自适应加权，解决异构奖励优化问题，进一步提升平均性能并保持通用能力。
GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
We present GoLongRL, a fully open-source, capability-oriented post-training recipe for long-context reinforcement learning with verifiable rewards (RLVR). Existing long-context RL methods often treat data construction as a matter of designing increasingly complex retrieval paths, leading to homogeneous task coverage and reward formulations that inadequately reflect practical long-context requirements. Our work offers two contributions. (1) Capability-oriented data construction with full open release. We openly release a dataset of 23K RLVR samples, the complete construction pipeline, and all training code. Guided by a taxonomy of long-context capabilities, the dataset spans 9 task types, each paired with its natural evaluation metric. It comprises curated open-source samples from established corpora and synthetic samples whose QA pairs are generated from real source documents such as books, academic papers, and multi-turn dialogues. Under the same vanilla GRPO setup, our dataset alone outperforms the closed-source QwenLong-L1.5 dataset. Moreover, our Qwen3-30B-A3B model trained on this data delivers long-context performance comparable to DeepSeek-R1-0528 and Qwen3-235B-A22B-Thinking-2507, suggesting that broader coverage and greater reward diversity substantially benefit long-context capability improvement. (2) TMN-Reweight for heterogeneous multitask optimization. To address optimization challenges from heterogeneous rewards, we propose TMN-Reweight, which combines task-level mean normalization for cross-task reward scale alignment with difficulty-adaptive weighting for more reliable advantage estimation. TMN-Reweight further improves average performance over vanilla GRPO, with general capabilities preserved or improved across reported evaluations.