4 papers
Knowledge Compounding: An Empirical Economic Analysis of Self-Evolving Knowledge Wikis under the Agentic ROI Framework
Shuide Wen, Beier Ku
Building on the Agentic ROI framework proposed by Liu et al. (2026), this paper introduces knowledge compounding as a new measurable concept in the empirical economics of LLM agent…
DLIOS: An LLM-Augmented Real-Time Multi-Modal Interactive Enhancement Overlay System for Douyin Live Streaming
Shuide Wen, Sungil Seok, Beier Ku +6
We present DLIOS, a Large Language Model (LLM)-augmented real-time multi-modal interactive enhancement overlay system for Douyin (TikTok) live streaming. DLIOS employs a three-laye…
From Visual Perception to Deep Empathy: An Automated Assessment Framework for House-Tree-Person Drawings Using Multimodal LLMs and Multi-Agent Collaboration
Shuide Wen, Yu Sun, Beier Ku +4
Background: The House-Tree-Person (HTP) drawing test, introduced by John Buck in 1948, remains a widely used projective technique in clinical psychology. However, it has long faced…
Neo-Grounded Theory: A Methodological Innovation Integrating High-Dimensional Vector Clustering and Multi-Agent Collaboration for Qualitative Research
Shuide Wen, Beier Ku, Teng Wang +2
Purpose: Neo Grounded Theory (NGT) integrates vector clustering with multi agent systems to resolve qualitative research's scale depth paradox, enabling analysis of massive dataset…