7 papers
When Not to Write Memory: Governing False Promotion from Correlated Agent Traces
Yijiashun Qi, Xiang Xu, Yuxuan Li
Long-lived language agents increasingly write reusable memories from their own execution traces. The key safety question is not only what agents should remember, but when they shou…
Coverage-Aware Web Crawling for Domain-Specific Supplier Discovery via a Web--Knowledge--Web Pipeline
Yijiashun Qi, Yijiazhen Qi, Tanmay Wagh
Identifying the full landscape of small and medium-sized enterprises (SMEs) in specialized industry sectors is critical for supply-chain resilience, yet existing business databases…
When Corrective Hints Hurt: Prompt Design in Reasoner-Guided Repair of LLM Overcaution on Entailed Negations under OWL~2~DL
Yijiashun Qi, Xiang Xu, Yuxuan Li
We report a reproducible error pattern in GPT-5.4 on OWL~2~DL compliance queries: the model frequently answers ``unknown'' when the reasoner-entailed answer is ``no'' under \emph{F…
Structured Memory Mechanisms for Stable Context Representation in Large Language Models
Yue Xing, Tao Yang, Yijiashun Qi +3
This paper addresses the limitations of large language models in understanding long-term context. It proposes a model architecture equipped with a long-term memory mechanism to imp…
Optimized Unet with Attention Mechanism for Multi-Scale Semantic Segmentation
Xuan Li, Quanchao Lu, Yankaiqi Li +2
Semantic segmentation is one of the core tasks in the field of computer vision, and its goal is to accurately classify each pixel in an image. The traditional Unet model achieves e…
Graph Neural Network-Driven Hierarchical Mining for Complex Imbalanced Data
Yijiashun Qi, Quanchao Lu, Shiyu Dou +3
This study presents a hierarchical mining framework for high-dimensional imbalanced data, leveraging a depth graph model to address the inherent performance limitations of conventi…