4 papers
Can Agent Memory Systems Track Evolving State?
Xinyi Fan, Miri Liu, Ruozhen Yang +2
As LLM-based agents are deployed for longer and higher-stakes tasks, their memory systems continue to have crucial gaps. While existing memory benchmarks focus largely on recall-sh…
Grounding Agent Memory in Contextual Intent
Ruozhen Yang, Yucheng Jiang, Yueqi Jiang +3
Deploying large language models in long-horizon, goal-oriented interactions remains challenging because similar entities and facts recur under different latent goals and constraint…
Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking
Yunyi Zhang, Ruozhen Yang, Siqi Jiao +2
Scientific paper retrieval is essential for supporting literature discovery and research. While dense retrieval methods demonstrate effectiveness in general-purpose tasks, they oft…
TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision
Yunyi Zhang, Ruozhen Yang, Xueqiang Xu +4
Hierarchical text classification aims to categorize each document into a set of classes in a label taxonomy, which is a fundamental web text mining task with broad applications suc…