Current Large Language Models (LLMs) are not only limited to some maximum context length, but also are not able to robustly consume long inputs. To address these limitations, we propose ReadAgent, an LLM agent system that increases effective context length up to 20x in our experiments. Inspired by how humans interactively read long documents, we implement ReadAgent as a simple prompting system that uses the advanced language capabilities of LLMs to (1) decide what content to store together in a memory episode, (2) compress those memory episodes into short episodic memories called gist memories, and (3) take actions to look up passages in the original text if ReadAgent needs to remind itself of relevant details to complete a task. We evaluate ReadAgent against baselines using retrieval methods, using the original long contexts, and using the gist memories. These evaluations are performed on three long-document reading comprehension tasks: QuALITY, NarrativeQA, and QMSum. ReadAgent outperforms the baselines on all three tasks while extending the effective context window by 3.5-20x.
From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学深圳校区）；Peng Cheng Laboratory（鹏城实验室）
FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding
College of Future Information Technology, Fudan University, Shanghai, China（复旦大学未来信息科技学院）；Shanghai Innovation Institute, Shanghai, China（上海创新研究院）；Shanghai Artificial Intelligence Laboratory, Shanghai, China（上海人工智能实验室）；The Chinese University of Hong Kong, Hong Kong, China（香港中文大学）
StreamingThinker: Large Language Models Can Think While Reading
Shanghai Jiao Tong University（上海交通大学）；Eastern Institute of Technology, Ningbo（宁波东部技术研究院）；Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Institute of Digital Twin（宁波空间智能与数字衍生关键实验室，数字孪生研究院）；Hong Kong Polytechnic University（香港理工大学）；Munich Center for Machine Learning, LMU（慕尼黑机器学习中心，莱茵-慕尼黑大学）
School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院）；College of Information Science and Technology and Artificial Intelligence, Nanjing Forestry University（南京林业大学信息科学技术与人工智能学院）
LLMs Struggle to Measure What Distinguishes Students of Different Proficiency Levels: A Study of Item Discrimination in Reading Comprehension Assessment
MBZUAI（穆罕默德·本·扎耶德人工智能大学）；University of Maryland（马里兰大学）；Virginia Tech（弗吉尼亚理工大学）
Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processing
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of California, Berkeley（加州大学伯克利分校）；University of Pennsylvania（宾夕法尼亚大学）
WaveFilter: Enhancing the Long-Context Capability of Diffusion LLMs via Wavelet-Guided KV Cache Filtering
Nanjing University of Science and Technology（南京理工大学）；Alibaba Group（阿里巴巴集团）；Huzhou Normal University（湖州师范学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Equipping Retrieval-Augmented Large Language Models with Document Structure Awareness
School of Computer Science, Beijing Institute of Technology（计算机学院，北京理工大学）；Ant Group（蚂蚁集团）；Southeast Academy of Information Technology, Beijing Institute of Technology（信息科技东南学院，北京理工大学）
ZJUKLAB at SemEval-2021 Task 4: Negative Augmentation with Language Model for Reading Comprehension of Abstract Meaning
Zhejiang University & AZFT Joint Lab for Knowledge Engine（浙江大学与AZFT联合知识引擎实验室）；Hangzhou Innovation Center, Zhejiang University（浙江大学杭州创新中心）；Microsoft（微软）
Synergizing Large Language Models and Task-specific Models for Time Series Anomaly Detection
Zhejiang University（浙江大学）；Department of Computer Science and Technology, Singapore Management University（新加坡管理大学计算机科学与技术系）；Department of Computer Science and Technology, National University of Singapore（新加坡国立大学计算机科学与技术系）
Document-Level Event Extraction via Human-Like Reading Process
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Beijing University of Posts and Telecommunications（北京邮电大学）
文档级事件提取（DEE）特别棘手，因为它带来了两个挑战：分散参数和多事件。第一个挑战意味着一个事件记录的参数可以驻留在文档中的不同句子中，而第二个挑战反映了一个文档可以同时包含多个这样的事件记录。本文从人类阅读认知的角度出发，提出了一种基于文本事件的人类阅读启发提取器（Human Reading inspired Extractor for Document Events，HRE），该方法将文本事件分解为粗读和精读两个迭代阶段。具体而言，第一阶段浏览文档以检测事件的发生，第二阶段用于提取特定的事件参数。对于每一个具体的事件角色，精细阅读从句子到字符分层工作，以确定跨句子的论点，从而解决分散的论点问题。同时，通过多轮的粗读探索，发现未检测到的事件，从而解决了多事件问题。实验结果表明，HRE优于以往的竞争方法。
End-to-End Lip Reading in Romanian with Cross-Lingual Domain Adaptation and Lateral Inhibition
University of Bucharest（布加勒斯特大学）；University Politehnica of Bucharest（布加勒斯特理工大学）；National Institute for Research and Development in Informatics - ICI Bucharest（布加勒斯特国家信息学研发研究院（ICI布加勒斯特））
MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering
School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Digital China Group（数字中国集团）
A Question Answering Approach to Emotion Cause Extraction
Shenzhen Graduate School, Harbin Institute of Technology（哈尔滨工业大学深圳研究生院）；College of Mathematics and Computer Science, Fuzhou University（福州大学数学与计算机科学学院）；School of Engineering and Applied Science, Aston University（阿斯顿大学工程与应用科学学院）；Guangdong Provincial Engineering Technology Research Center for Data Science（广东省数据科学工程技术研究中心）；Department of Computing, the Hong Kong Polytechnic University（香港理工大学计算学系）
AlphaOracle: Oracle bone script decipherment via human-workflow-inspired deep learning
School of Software Engineering, Huazhong University of Science and Technology（华中科技大学软件学院）；School of Electronic Information Engineering, South China University of Technology（华南理工大学电子信息学院）；Key Laboratory of Oracle Bone Inscriptions Information Processing, Anyang Normal University（安阳师范学院甲骨文信息处理重点实验室）
