长程对话智能体需要通过与用户交互不断演化的事件、任务和目标进行互动。这些历史记录本质上是时间性的,然而许多现有的记忆系统主要按主题相似性组织信息,可能忽略事件发生的顺序。我们引入线段树记忆(Segment Tree Memory,简称SegTreeMem),这是一种将对话历史表示为按时间顺序排列的线段树的记忆架构。SegTreeMem通过在线最右边缘更新规则逐步插入新话语,在形成层次化记忆片段的同时保持时间顺序。在检索时,SegTreeMem通过树传播相关性分数,将局部语义匹配与层次化时间上下文相结合。在三个长程记忆基准和两个LLM骨干网络上,SegTreeMem在答案质量上优于平面检索、图结构记忆和树结构记忆基线。额外的时间顺序排列分析表明,性能提升依赖于在记忆构建过程中保持时间顺序,这支持了时间顺序是智能体记忆关键结构的观点。
英文摘要:
Long-horizon conversational agents need to interact with users through evolving events, tasks, and goals. Such histories are naturally temporal, yet many existing memory systems organize information primarily by topical similarity and may ignore the order in which events occur. We introduce Segment Tree Memory, or SegTreeMem, a memory architecture that represents conversation history as a temporally ordered Segment Tree over utterances. SegTreeMem incrementally inserts new utterances through an online rightmost-frontier update rule, preserving chronological order while forming hierarchical memory segments. For retrieval, SegTreeMem propagates relevance scores through the tree to combine local semantic matching with hierarchical temporal context. Across three long-horizon memory benchmarks and two LLM backbones, SegTreeMem improves answer quality over flat retrieval, graph-structured memory, and tree-structured memory baselines. Additional temporal-order permutation analysis shows that the performance gain depends on preserving temporal order during memory construction, supporting the claim that temporal order is a key structure for agentic memory.
A Security Analysis of Long-Horizon Agentic AI Systems: Threats, Evaluation, and Framework Development
Department of Computer Science, College of Computers and Information Technology, Taif University, KSA (Summer 2026)(计算机科学系,计算机与信息科技学院,泰夫大学,沙特阿拉伯(2026年夏季))
HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning
Aerospace Information Research Institute, Chinese Academy of Sciences(中国科学院航空航天信息研究所);University of Chinese Academy of Sciences(中国科学院大学);Tencent Hunyuan(腾讯文脉);School of Computer Science and Technology, Tianjin University(天津大学计算机科学与技术学院)
AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing
National Engineering Research Center of Software Engineering, Peking University(北京大学国家软件工程研究中心);School of Computer Science, Peking University(北京大学计算机学院)
Consistent Plan-Act for Long-Horizon Agentic Tasks
Nanjing University(南京大学);National Key Laboratory for Novel Software Technology, Nanjing University(南京大学计算机软件新技术全国重点实验室);Meituan(美团);University of Science and Technology of China(中国科学技术大学)
Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
School of Computer Science and Technology, Beijing Jiaotong University(北京交通大学计算机科学与技术学院);Hithink Research(慧思科技);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Huawei Noah’s Ark Lab(华为诺亚实验室);Peng Cheng Lab(鹏城实验室)
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Meituan(美团);MBZUAI(Mohamed bin Zayed University of Artificial Intelligence);Huazhong University of Science and Technology(华中科技大学);Peking University(北京大学);Tsinghua University(清华大学);The Chinese University of Hong Kong(香港中文大学);Shanghai Jiao Tong University(上海交通大学)
RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades
UniPat AI;Peking University(北京大学);Fudan University(复旦大学);The University of Hong Kong(香港大学);Tsinghua University(清华大学);G Labs(0G实验室);Pipeline Lab(Pipeline实验室)
SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
Tsinghua University(清华大学);Peking University(北京大学);Ant Group(蚂蚁集团);Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院)