张轩｜清华大学｜学者主页

2026

AutoCompact: Learning When to Compact Context in Long-Horizon Coding Agents

Xuan Zhang, Longtao Zheng, Cunxiao Du, Bo An, Xin Dong

arXiv preprint

2026

Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning

Xuan Zhang, Zhijian Zhou, Lingfeng Qiao, Yulei Qin, Ke Li, Xing Sun, Xiaoyu Tan, Chao Qu, Yuan Qi

arXiv preprint

2026

Self-Evolving World Models for LLM Agent Planning

Xuan Zhang, Wenxuan Zhang, See-Kiong Ng, Yang Deng

arXiv preprint

2026

A Comparative Evaluation of AI Agent Security Guardrails

Qi Li, Jiu Li, Pingtao Wei, Jianjun Xu, Xueyi Wei, Jiwei Shi, Xuan Zhang, Yanhui Yang, Xiaodong Hui, Peng Xu, Lingquan Zhou

arXiv preprint

2026

I'll Keep an Ear Out: Teaching AudioLLMs Proactive Audio Assistance

Amit Kumar Singh Yadav, Ritvik Shrivastava, Xuan Zhang, Seungwhan Moon, Shashank Jain, Pinar Donmez, Babak Damavandi

arXiv preprint

2026

Event-Aligned Visual Action Reasoning for World Action Models

Xiaomeng Yang, Yushu Wu, Yi Gao, Yuhao Lei, Xuan Zhang, Pu Zhao, Yanzhi Wang

arXiv preprint

2026

LSR-Ben: A Logical and Scientific Reasoning Benchmark for Evaluating Process Reward Models

Zhouhao Sun, Xuan Zhang, Xiao Ding, Bibo Cai, Li Du, Kai Xiong, Xinran Dai, Fei Zhang, weidi tang, Zhiyuan Kan, Yang Zhao, Bing Qin, Ting Liu

arXiv preprint

2026

Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning

Daiqing Wu, Xuan Zhang, Dongbao Yang, Jiashu Yao, Longfei Chen, Qingsong Liu, Sicheng Zhao, Can Ma, Yangyang Kang, Yu Zhou

arXiv preprint

2026

Clarify the User or Verify the World? Uncertainty Routing for Proactive Agents

Zhaofeng Li, Xuan Zhang, Xiaokui Xiao, Yang Deng

arXiv preprint

2026

COPC: Coupled Off-Policy Correction for Asynchronous LLM Reinforcement Learning

Zicheng Hu, Zhijian Zhou, Xuan Zhang, Yuchen Liu, Cheng Chen, Yuan Li, Qi Gu, Yan Feng, Hongyan Hao, Chao Qu

arXiv preprint

2026

Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates

Yibo Li, Zijie Lin, Ailin Deng, Xuan Zhang, Yufei He, Shuo Ji, Tri Cao, Bryan Hooi

arXiv preprint

2025

Constraints-Guided Diffusion Reasoner for Neuro-Symbolic Learning

Xuan Zhang, Zhijian Zhou, Weidi Xu, Yanting Miao, Chao Qu, Yuan Qi

arXiv preprint

2025

AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification

Xuan Zhang, Yongliang Shen, Zhe Zheng, Linjuan Wu, Wenqi Zhang, Yuchen Yan, Qiuying Peng, Jun Wang, Weiming Lu

arXiv preprint

2025

PICE: A Semantic-Driven Progressive Inference System for LLM Serving in Cloud-Edge Networks

Huiyou Zhan, Xuan Zhang, Haisheng Tan, Han Tian, Dongping Yong, Junyang Zhang, Xiang-Yang Li

arXiv preprint

2025

Count Counts: Motivating Exploration in LLM Reasoning with Count-based Intrinsic Rewards

Xuan Zhang, Ruixiao Li, Zhijian Zhou, Long Li, Yulei Qin, Ke Li, Xing Sun, Xiaoyu Tan, Chao Qu, Yuan Qi

arXiv preprint

2025

Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs

Xuan Zhang, Cunxiao Du, Sicheng Yu, Jiawei Wu, Fengzhuo Zhang, Wei Gao, Qian Liu

arXiv preprint

2025

Multilingual Agent-Based World Modeling for Social Science

Xuan Zhang, Wenxuan Zhang, Anxu Wang, See-Kiong Ng, Yang Deng

arXiv preprint

2025

BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms

Yunlong Hou, Fengzhuo Zhang, Cunxiao Du, Xuan Zhang, Jiachun Pan, Tianyu Pang, Chao Du, Vincent Y. F. Tan, Zhuoran Yang

arXiv preprint

2025

FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding

Yanan Guo, Wenhui Dong, Jun Song, Shiding Zhu, Xuan Zhang, Hanqing Yang, Yingbo Wang, Yang Du, Xianing Chen, Bo Zheng

arXiv preprint

2025

Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment

Hua Ye, Hang Ding, Siyuan Chen, Yiyang Jiang, Changyuan Zhang, Xuan Zhang

arXiv preprint

2025

Universal Retrieval for Multimodal Trajectory Modeling

Xuan Zhang, Ziyan Jiang, Rui Meng, Yifei Leng, Zhenbang Xiao, Zora Zhiruo Wang, Yanyi Shang, Dehan Kong

arXiv preprint

2024

LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation

Xuan Zhang, Fengzhuo Zhang, Cunxiao Du, Chao Du, Tianyu Pang, Wei Gao, Min Lin

arXiv preprint

2024

Reinforcement Retrieval Leveraging Fine-grained Feedback for Fact Checking News Claims with Black-Box LLM

Xuan Zhang, Wei Gao

arXiv preprint

2024

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs

Xuan Zhang, Chao Du, Tianyu Pang, Qian Liu, Wei Gao, Min Lin

arXiv preprint

2024

Predicting Viral Rumors and Vulnerable Users for Infodemic Surveillance

Xuan Zhang, Wei Gao

arXiv preprint

2024

On the Multi-turn Instruction Following for Conversational Web Agents

Yang Deng, Xuan Zhang, Wenxuan Zhang, Yifei Yuan, See-Kiong Ng, Tat-Seng Chua

arXiv preprint

2024

Ask-before-Plan: Proactive Language Agents for Real-World Planning

Xuan Zhang, Yang Deng, Zifeng Ren, See-Kiong Ng, Tat-Seng Chua

arXiv preprint

2023

Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method

Xuan Zhang, Wei Gao

arXiv preprint

张轩

精选作品

期刊论文

面向未充分标注数据的机器学习方法研究

预印本

AutoCompact: Learning When to Compact Context in Long-Horizon Coding Agents

Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning

Self-Evolving World Models for LLM Agent Planning

A Comparative Evaluation of AI Agent Security Guardrails

I'll Keep an Ear Out: Teaching AudioLLMs Proactive Audio Assistance

Event-Aligned Visual Action Reasoning for World Action Models

LSR-Ben: A Logical and Scientific Reasoning Benchmark for Evaluating Process Reward Models

Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning

Clarify the User or Verify the World? Uncertainty Routing for Proactive Agents

COPC: Coupled Off-Policy Correction for Asynchronous LLM Reinforcement Learning

Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates

Constraints-Guided Diffusion Reasoner for Neuro-Symbolic Learning

AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification

PICE: A Semantic-Driven Progressive Inference System for LLM Serving in Cloud-Edge Networks

Count Counts: Motivating Exploration in LLM Reasoning with Count-based Intrinsic Rewards

Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs

Multilingual Agent-Based World Modeling for Social Science

BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms

FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding

Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment

Universal Retrieval for Multimodal Trajectory Modeling

LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation

Reinforcement Retrieval Leveraging Fine-grained Feedback for Fact Checking News Claims with Black-Box LLM

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs

Predicting Viral Rumors and Vulnerable Users for Infodemic Surveillance

On the Multi-turn Instruction Following for Conversational Web Agents

Ask-before-Plan: Proactive Language Agents for Real-World Planning

Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method