license, library_name, pipeline_tag, datasets

license	library_name	pipeline_tag	datasets
mit	transformers	text-generation	Kwai-Klear/GoLongRL

✨ GoLongRL-30B-A3B

We present GoLongRL, a fully open-source, capability-oriented post-training recipe for long-context reinforcement learning with verifiable rewards (RLVR).

Resource	Link
📝 Paper	ArXiv 2605.19577
🤗 Daily Paper	Hugging Face Paper
💻 Code	GitHub Repository
📂 Project	HF Collection
🤗 Model Hub	GoLongRL-4B
🤗 Dataset Hub	GolongRL Dataset
📧 Contact	xiao_xuan_zi_666@163.com & suzhenpeng13@163.com

📌 Overview

_{Overall performance comparison on long-context benchmarks (DocMath, LongBench-V2, Frames, MRCR, CorpusQA, LBV1-QA).}

GoLongRL-30B-A3B achieves strong long-context performance at the 30B scale.

Model	Avg.	DocMath	LBV2	Frames	MRCR	CorpusQA	LBV1-QA
Qwen3-30B-A3B-Thinking-2507	60.1	63.3	48.7	70.2	41.6	70.5	66.5
DeepSeek-R1-0528	68.7	63.4	59.5	76.9	64.9	77.5	69.9
Qwen3-235B-A22B-Thinking	68.5	65.8	57.5	75.1	66.2	75.3	70.9
Gemini-2.5-Flash-Thinking	68.7	64.8	56.8	65.8	78.8	79.4	66.9
QwenLong-L1.5 (w. GRPO)	67.2	65.1	55.3	71.4	66.9	76.9	67.9
GoLongRL-30B-A3B (Ours)	69.8	65.3	55.1	74.5	81.6	73.6	68.7

Our framework combines the following:

1. Capability-Oriented Dataset (23K samples, 9 task types). Guided by a taxonomy of long-context capabilities, the dataset covers precise retrieval, comprehension, exhaustive retrieval, numerical reasoning, structured extraction, structured matching, graded ranking, sequence ordering, and summarization. Each task is paired with its natural evaluation metric as the reward function.

2. TMN-Reweight. 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.

3. Full Open Release. We publicly release the complete dataset, the four-phase construction pipeline, and all training code.

Key Results

• Under the same vanilla GRPO setup, our dataset alone outperforms the closed-source QwenLong-L1.5 dataset at both 4B and 30B scales.
• TMN-Reweight further improves average performance over vanilla GRPO, with general capabilities preserved or improved across reported evaluations.
• Substantial gains on dialogue memory (LongMemEval +13.6) and agentic memory benchmarks.

🔍 Evaluation

Evaluation uses QwenLong-Benchmarks, covering three capability dimensions:

Dimension	Benchmarks
Long-Context	LongBench-V2, MRCR (≤128K / 128K–512K / 512K–1M), Frames, LongBench QA, DocMath, CorpusQA (≤128K / ≤1M)
General	MMLU-Pro, AIME 2024/2025, GPQA-Diamond
Memory	BFCL-V4 (memory subset), LongMemEval

🤝 Citation

@misc{lv2026golongrlcapabilityorientedlongcontext,
      title={GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment}, 
      author={Minxuan Lv and Tiehua Mei and Tanlong Du and Junmin Chen and Zhenpeng Su and Ziyang Chen and Ziqi Wang and Zhennan Wu and Ruotong Pan and jian Liang and Ruiming Tang and Han Li},
      year={2026},
      eprint={2605.19577},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2605.19577}, 
}