用信念与策略声明式控制LLM流水线，打造可解释、可调控的AI流程新范式。
arXiv:2604.14401v2 Announce Type: replace Abstract: Agentic AI systems are becoming commonplace in domains that require long-lived, stateful decision-…
提出统一静态与动态剪枝的框架，显著提升大模型推理速度与资源效率。
arXiv:2607.21985v1 Announce Type: cross Abstract: The increasing deployment of large language models (LLMs) has magnified the computational and memory…
这篇被VLDB 2026录用的论文，将Git版本控制思想引入数据湖，为代理湖屋（agentic lakehouse）提供数据版本管理新范式。
arXiv:2607.08319v1 Announce Type: cross Abstract: We present GitLake, a Git-for-data design for an agent-first lakehouse. The system lifts single-tabl…
聚焦语义连接优化，为异构数据查询性能提升提供新思路，数据库领域前沿研究。
arXiv:2606.29532v1 Announce Type: cross Abstract: Integrating unstructured data into relational database systems is increasingly important as demand g…
VLDB 2026 Demo论文，提出端到端数据分析智能体系统DA-Studio，打通数据获取到洞察全流程。
arXiv:2606.31423v1 Announce Type: cross Abstract: Real-world data analysis is a multi-step process over heterogeneous inputs rather than merely produc…
专为有状态LLM应用设计的记忆基础管理系统，VLDB26接收的高质量学术论文
arXiv:2605.29640v1 Announce Type: new Abstract: Large Language Models have revolutionized interactive applications; however, their finite context wind…
AI智能体记忆系统新突破：分层时间索引实现高效检索，专为长时间任务优化。
arXiv:2605.23986v1 Announce Type: cross Abstract: Memory is a fundamental component for enabling long-context LLM agents, supporting persistent state …