papers

Publications (10)

cs.CL2026

Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents

Heng Zhou, Zelin Tan, Zhemeng Zhang +15

When an LLM-based agent improves on a task, is the gain from the model itself or from the reasoning paradigm wrapped around it? We study this question by comparing six inference-ti…

cs.HC2026

ParaTutor: Coordinating Parent and Child Math Tutoring through Role Separated LLM Scaffolding

Lan Luo, Anqi Wang, Muzhi Zhou +4

ParaTutor is an LLM‑driven tutoring system that provides role‑specific scaffolding for parents and children during home math word‑problem sessions, using strategy prompts for paren…

#parent‑child tutoring#math word problems#role‑sensitive scaffolding#large language models
cs.LG2026

Edu-Theater: A Data-Efficient Agent Framework for Scalable Learner Behavior Simulation through Staging Roll-Call

Weibo Gao, Qi Liu, Linan Yue +6

Large-scale learner-task interaction data are crucial for intelligent educational systems but are costly to collect and constrained by privacy and learner engagement. Learner simul…

cs.CY2024

Interoperability of the Metaverse: A Digital Ecosystem Perspective Review

Liang Yang, Shi-Ting Ni, Yuyang Wang +3

The Metaverse is at the vanguard of the impending digital revolution, with the potential to significantly transform industries and lifestyles. However, in 2023, skepticism surfaced…

cs.CV2026

BridgeDiff: Bridging Human Observations and Flat-Garment Synthesis for Virtual Try-Off

Shuang Liu, Ao Yu, Linkang Cheng +5

Virtual try-off (VTOFF) aims to recover canonical flat-garment representations from images of dressed persons for standardized display and downstream virtual try-on. Prior methods…

cs.CV2026

Reading Seeing: Diagnosing and Closing the Typography Gap in Vision-Language Models

Heng Zhou, Ao Yu, Li Kang +5

Vision-Language Models achieve near-perfect accuracy at reading text in images, yet prove largely typography-blind: capable of recognizing what text says, but not how it looks. We…

cs.CL2025

LiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledge

Heng Zhou, Ao Yu, Yuchen Fan +10

Evaluating large language models (LLMs) on question answering often relies on static benchmarks that reward memorization and understate the role of retrieval, failing to capture th…

cs.MM2026

Toward Site-Aware MR Art Exhibitions: A SLAM-Based Deployment Pipeline for Spatial Coherence and Exhibition Experience

Yawei Zhao, Yuming Zhu, Hao Li +4

Mixed Reality (MR) is increasingly being used in exhibition settings to bring digital artworks into relation with the physical environment. However, existing MR exhibition systems…

cs.HC2025

Exploring LLM-Powered Role and Action-Switching Pedagogical Agents for History Education in Virtual Reality

Zihao Zhu, Ao Yu, Xin Tong +1

Multi-role pedagogical agents can create engaging and immersive learning experiences, helping learners better understand knowledge in history learning. However, existing pedagogica…

cs.RO2026

Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning

Heng Zhou, Li Kang, Yiran Qin +12

Understanding the world from distributed, partial viewpoints is a fundamental challenge for embodied multi-agent systems. Each agent perceives the environment through an ego-centri…