在本文中，我们介绍了边缘书写（WiM），这是一种为大型语言模型设计的新型推理模式，旨在优化面向检索任务中对长输入序列的处理。该方法利用键值缓存的分块预填充来执行分段推理，从而能够高效处理广泛的上下文，并生成和分类指导模型执行特定任务的中间信息（“边缘”）。此方法在略微增加计算开销的同时，显著提升了现成模型的性能，且无需微调。具体而言，我们观察到WiM在推理技能（HotpotQA、MultiHop-RAG）上平均提高了7.5%的准确率，在聚合任务（CWE）上F1分数提升了30.0%以上。此外，我们展示了所提出的模式如何契合交互式检索设计，该设计为最终用户提供关于上下文处理进度的持续更新，并精准指出相关信息如何整合到最终响应中。我们在 https://github.com/writer/writing-in-the-margins 上发布了使用Hugging Face Transformers库的WiM实现。
英文摘要：
In this paper, we introduce Writing in the Margins (WiM), a new inference pattern for Large Language Models designed to optimize the handling of long input sequences in retrieval-oriented tasks. This approach leverages the chunked prefill of the key-value cache to perform segment-wise inference, which enables efficient processing of extensive contexts along with the generation and classification of intermediate information ("margins") that guide the model towards specific tasks. This method increases computational overhead marginally while significantly enhancing the performance of off-the-shelf models without the need for fine-tuning. Specifically, we observe that WiM provides an average enhancement of 7.5% in accuracy for reasoning skills (HotpotQA, MultiHop-RAG) and more than a 30.0% increase in the F1-score for aggregation tasks (CWE). Additionally, we show how the proposed pattern fits into an interactive retrieval design that provides end-users with ongoing updates about the progress of context processing, and pinpoints the integration of relevant information into the final response. We release our implementation of WiM using Hugging Face Transformers library at https://github.com/writer/writing-in-the-margins.
Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning
Institute for AI Industry Research (AIR)（人工智能产业研究院）；Tsinghua University（清华大学）；Dept. of Comp. Sci. & Tech.（计算机科学与技术系）；Institute for AI（人工智能研究院）；Institute of Intelligent Computing（智能计算研究院）；Alibaba Group（阿里巴巴集团）
CoAuthorAI: A Human in the Loop System For Scientific Book Writing
Kexin Technology, Beijing（凯欣科技，北京）；Institute for Sustainable Industries and Liveable Cities, Victoria University（可持续产业与宜居城市研究所，维多利亚大学）；School of Information Technology, Deakin University（信息科技学院，德坎大学）
Shared Worlds, Private Minds: Structured Memory for Long-Form Writing as World Creation
Southeast University（东南大学）；Beijing Zhongguancun Academy（北京中关村学院）；Duke University（杜克大学）；East China Normal University（华东师范大学）；Renmin University of China（中国人民大学）；Communication University of China（中国传媒大学）；Jiangsu Second Normal University（江苏第二师范学院）；ZhuiWen Technology Co., Ltd.（追闻科技有限公司）
SparkRA: A Retrieval-Augmented Knowledge Service System Based on Spark Large Language Model
iFLYTEK Research（讯飞研究院）；University of Science and Technology of China（中国科学技术大学）；Harbin Institute of Technology（哈尔滨工业大学）；National Science Library, Chinese Academy of Sciences（中国科学院国家科学图书馆）
Overview of PAN 2026: Voight-Kampff Generative AI Detection, Text Watermarking, Multi-Author Writing Style Analysis, Generative Plagiarism Detection, and Reasoning Trajectory Detection
Friedrich Schiller University Jena（耶纳弗里德里希·施勒格尔大学）；University of Applied Sciences BFI（应用科学大学BFI）；Mohamed bin Zayed University of Artificial Intelligence（马尔代夫 bin Zayed 人工智能大学）；University of Kassel（卡塞尔大学）；INSAIT, Sofia University ``St. Kliment Ohridski''（INSAIT，索菲亚大学『圣克莱门特·奥赫里迪斯』）；University of Innsbruck（因斯布鲁克大学）
PAN 2026旨在通过客观评估推进计算风格学和文本取证，涵盖生成式AI检测、文本水印、多作者写作分析、抄袭检测及推理轨迹检测等五个新旧任务。
SEAL: Scaling to Emphasize Attention for Long-Context Retrieval
Department of Convergence IT Engineering（融合IT工程系）；Department of Computer Science and Engineering（计算机科学与工程系）；Graduate School of Artificial Intelligence（人工智能研究生院）
MODOC: A Modular Interface for Flexible Interlinking of Text Retrieval and Text Generation Functions
Institute of Neuroinformatics, University of Zurich and ETH Zurich（苏黎世大学与苏黎世联邦理工学院神经信息学研究所）；ETH Zurich（苏黎世联邦理工学院）；Linguistic Research Infrastructure, University of Zurich（苏黎世大学语言研究基础设施）
Personalized Text Generation with Contrastive Activation Steering
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Northeastern University（东北大学）；University of Science and Technology of China（中国科学技术大学）；National University of Singapore（新加坡国立大学）
