QwenLong-L1: Towards Long-Context Large Reasoning Models with
  Reinforcement Learning

Fanqi Wan; Weizhou Shen; Shengyi Liao; Yingcheng Shi; Chenliang Li; Ziyi Yang; Ji Zhang; Fei Huang; Jingren Zhou; Ming Yan

Paper · arXiv 2505.17667

QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning

Fanqi Wan, Weizhou Shen, Shengyi Liao, Yingcheng Shi, Chenliang Li, Ziyi Yang, Ji Zhang, Fei Huang, Jingren Zhou, Ming Yan

89 upvotesMay 23, 2025arXiv 预印本

AI 摘要

A framework called QwenLong-L1 enhances large reasoning models for long-context reasoning through reinforcement learning, achieving leading performance on document question-answering benchmarks.

reinforcement learninglong-context reasoningshort-context reasoningtraining efficiencyoptimization processQwenLong-L1progressive context scalingsupervised fine-tuningcurriculum-guided phased RLdifficulty-aware retrospective samplingdocument question-answering benchmarksOpenAI-o3-miniQwen3-235B-A22BClaude-3.7-Sonnet-Thinking

Abstract

Recent large reasoning models (LRMs) have demonstrated strong reasoning capabilities through reinforcement learning (RL). These improvements have primarily been observed within the short-context reasoning tasks. In contrast, extending LRMs to effectively process and reason on long-context inputs via RL remains a critical unsolved challenge. To bridge this gap, we first formalize the paradigm of long-context reasoning RL, and identify key challenges in suboptimal training efficiency and unstable optimization process. To address these issues, we propose QwenLong-L1, a framework that adapts short-context LRMs to long-context scenarios via progressive context scaling. Specifically, we utilize a warm-up supervised fine-tuning (SFT) stage to establish a robust initial policy, followed by a curriculum-guided phased RL technique to stabilize the policy evolution, and enhanced with a difficulty-aware retrospective sampling strategy to incentivize the policy exploration. Experiments on seven long-context document question-answering benchmarks demonstrate that QwenLong-L1-32B outperforms flagship LRMs like OpenAI-o3-mini and Qwen3-235B-A22B, achieving performance on par with Claude-3.7-Sonnet-Thinking, demonstrating leading performance among state-of-the-art LRMs. This work advances the development of practical long-context LRMs capable of robust reasoning across information-intensive environments.