QwenLong-L1.5：面向長上下文推理與記憶管理的訓練後優化方案

摘要

我們推出QwenLong-L1.5模型，該模型通過系統化的訓練後創新實現了卓越的長上下文推理能力。其核心技術突破包括：（1）長上下文數據合成管線：開發系統化合成框架，生成需要對全局分佈證據進行多跳溯因的挑戰性推理任務。通過將文檔解構為原子事實及其底層關聯，再以程式化方式組合可驗證的推理問題，我們的方法能大規模創建高質量訓練數據，顯著超越簡單檢索任務，實現真正的長程推理能力。（2）長上下文訓練的穩定性強化學習：為克服長上下文RL的關鍵不穩定性，我們引入任務平衡抽樣與任務特定優勢估計以減輕獎勵偏差，並提出自適應熵控策略優化（AEPO）動態調控探索-利用權衡。（3）超長上下文的記憶增強架構：針對擴展上下文窗口仍無法容納無限長序列的難題，我們開發具多階段融合RL訓練的記憶管理框架，無縫整合單次推理與基於記憶的迭代處理，可處理超過400萬詞元的任務。基於Qwen3-300億-A3B思維架構的QwenLong-L1.5在長上下文推理基準測試中達到與GPT-5和Gemini-2.5-Pro相當的性能，較基線模型平均提升9.90分。在超長任務（100萬至400萬詞元）上，其記憶智能體框架相比智能體基線帶來9.48分增益。此外，所獲得的長上下文推理能力還轉化為科學推理、記憶工具使用及長對話等通用領域的性能提升。

English

We introduce QwenLong-L1.5, a model that achieves superior long-context reasoning capabilities through systematic post-training innovations. The key technical breakthroughs of QwenLong-L1.5 are as follows: (1) Long-Context Data Synthesis Pipeline: We develop a systematic synthesis framework that generates challenging reasoning tasks requiring multi-hop grounding over globally distributed evidence. By deconstructing documents into atomic facts and their underlying relationships, and then programmatically composing verifiable reasoning questions, our approach creates high-quality training data at scale, moving substantially beyond simple retrieval tasks to enable genuine long-range reasoning capabilities. (2) Stabilized Reinforcement Learning for Long-Context Training: To overcome the critical instability in long-context RL, we introduce task-balanced sampling with task-specific advantage estimation to mitigate reward bias, and propose Adaptive Entropy-Controlled Policy Optimization (AEPO) that dynamically regulates exploration-exploitation trade-offs. (3) Memory-Augmented Architecture for Ultra-Long Contexts: Recognizing that even extended context windows cannot accommodate arbitrarily long sequences, we develop a memory management framework with multi-stage fusion RL training that seamlessly integrates single-pass reasoning with iterative memory-based processing for tasks exceeding 4M tokens. Based on Qwen3-30B-A3B-Thinking, QwenLong-L1.5 achieves performance comparable to GPT-5 and Gemini-2.5-Pro on long-context reasoning benchmarks, surpassing its baseline by 9.90 points on average. On ultra-long tasks (1M~4M tokens), QwenLong-L1.5's memory-agent framework yields a 9.48-point gain over the agent baseline. Additionally, the acquired long-context reasoning ability translates to enhanced performance in general domains like scientific reasoning, memory tool using, and extended dialogue.

QwenLong-L1.5：面向長上下文推理與記憶管理的訓練後優化方案

QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management

摘要

Support