14 papers
DocMaster: A Hierarchical Structure-Aware System for Document Analysis
Ziqi Chen, Yingli Zhou, Fangyuan Zhang +3
Leveraging large language models (LLMs) to analyze complex documents -- such as academic papers, technical manuals, and financial reports -- has emerged as a mainstream and critica…
HETERQA: Benchmarking Record Retrieval over Multiple Heterogeneous Sources
Yaodong Su, Hanchang Li, Quanqing Xu +2
In emerging systems (e.g., social media and e-commerce platforms), data records are often drawn from heterogeneous sources, such as relational tables, text documents, image reposit…
Maintaining Leiden Communities in Large Dynamic Graphs
Chunxu Lin, Yumao Xie, Yixiang Fang +3
Community detection is a foundational capability in large-scale industrial graph analytics, powering applications such as fraud-ring discovery, recommendation systems, and hierarch…
A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
Yingli Zhou, Wang Shu, Yaodong Su +3
Large language model (LLM)-based agents that reason, plan, and act through tools, memory, and structured interaction are emerging as a promising paradigm for automating complex wor…
H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure
Jiawei Yu, Yixiang Fang, Xilin Liu +1
Memory data are ubiquitous in Large Language Model (LLM)-based agents (e.g., OpenClaw and Manus). A few recent works have attempted to exploit agents'memory for improving their per…
ASTRA-QA: A Benchmark for Abstract Question Answering over Documents
Shu Wang, Shansong Zhou, Xinyang Wang +3
Document-based question answering (QA) increasingly includes abstract questions that require synthesizing scattered information from long documents or across multiple documents int…