QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management
arxiv.org · 5,747 words · saved by 1 readers
N/A
December 16, 2025 QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management Weizhou Shen∗ Ziyi Yang∗ Chenliang Li∗ Zhiyuan Lu Miao Peng Huashan Sun Yingcheng Shi Shengyi Liao Shaopeng Lai Bo Zhang Dayiheng Liu Fei Huang…
saved by
related reading
- DeepSeek-R1arxiv.org
- State of RL for reasoning LLMs | A. Weersaweers.de
- [2603.21972] Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipearxiv.org
- [2510.11696] QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMsarxiv.org
- [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
- [2605.15156] MeMo: Memory as a Modelarxiv.org
- [2505.17373] Value-Guided Search for Efficient Chain-of-Thought Reasoningarxiv.org
- [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
- What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Studyarxiv.org
- Reasoning in General Domains without Verifiersarxiv.org
- You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectoriesarxiv.org
- Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Modelsarxiv.org