activity
20242026
most citedAn LLM-based Simulation Framework for Embodied Conversational Agents in Psychological Counseling

1 citations · 1 across the 4 of their papers we have counts for

collaborators

6 papers

cs.IR2026

GroupRAG: Cognitively Inspired Group-Aware Retrieval and Reasoning via Knowledge-Driven Problem Structuring

Xinyi Duan, Yuanrong Tang, Jiangtao Gong

The performance of language models is commonly limited by insufficient knowledge and constrained reasoning. Prior approaches such as Retrieval-Augmented Generation (RAG) and Chain-…

cs.HC2026

Human Tool: An MCP-Style Framework for Human-Agent Collaboration

Yuanrong Tang, Huiling Peng, Bingxi Zhao +5

Human-AI collaboration faces growing challenges as AI systems increasingly outperform humans on complex tasks, while humans remain responsible for orchestration, validation, and de…

cs.HC2026

Evaluating Text-based Conversational Agents for Mental Health: A Systematic Review of Metrics, Methods and Usage Contexts

Jiangtao Gong, Xiao Wen, Fengyi Tao +3

Text-based conversational agents (CAs) are increasingly used in mental health, yet evaluation practices remain fragmented. We conducted a PRISMA-guided systematic review (May-June…

cs.HC20251 cited

An LLM-based Simulation Framework for Embodied Conversational Agents in Psychological Counseling

Lixiu Wu, Yuanrong Tang, Qisen Pan +6

Due to privacy concerns, open dialogue datasets for mental health are primarily generated through human or AI synthesis methods. However, the inherent implicit nature of psychologi…

cs.HC2025

CA+: Cognition Augmented Counselor Agent Framework for Long-term Dynamic Client Engagement

Yuanrong Tang, Yu Kang, Yifan Wang +3

Current AI counseling systems struggle with maintaining effective long-term client engagement. Through formative research with counselors and a systematic literature review, we ide…

cs.CV2024

Large Language Models Powered Context-aware Motion Prediction in Autonomous Driving

Xiaoji Zheng, Lixiu Wu, Zhijie Yan +5

Motion prediction is among the most fundamental tasks in autonomous driving. Traditional methods of motion forecasting primarily encode vector information of maps and historical tr…