4 papers
SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory
Juntong Wang, Haoyue Zhao, guanghui Pan +4
Long-term memory is becoming a central bottleneck for language agents. Exsting RAG and GraphRAG systems largely treat memory graphs as static retrieval middleware, which limits the…
Not All Instances Are Equally Valuable: Towards Influence-Weighted Dataset Distillation
Qiyan Deng, Changqian Zheng, Lianpeng Qiao +3
Dataset distillation condenses large datasets into synthetic subsets, achieving performance comparable to training on the full dataset while substantially reducing storage and comp…
Unstructured Data Analysis using LLMs: A Comprehensive Benchmark
Qiyan Deng, Jianhui Li, Chengliang Chai +9
Nowadays, the explosion of unstructured data presents immense analytical value. Leveraging the remarkable capability of large language models (LLMs) in extracting attributes of str…
QUEST: Query Optimization in Unstructured Document Analysis
Zhaoze Sun, Qiyan Deng, Chengliang Chai +6
Most recently, researchers have started building large language models (LLMs) powered data systems that allow users to analyze unstructured text documents like working with a datab…