A Retraining-Free Framework for Analyzing Training Order Effects in Large Language Models
Hao Yang, Haoxuan Li, Mengyue Yang, Xu Chen, Mingming Gong
Conference on Empirical Methods in Natural Language Processing (EMNLP-findings)
Coding the Next Wave of Intelligence
Introduction
AI Engine Lab is a research team at Gaoling School of Artificial Intelligence, Renmin University of China. Our team is driven by a passion for technological advancement and innovation.
We hope that through our efforts, we can provide more in-depth, equitable and reliable methods and strategies for artificial intelligence. Our research directions include large language models, causal inference and recommender systems.
Openings: we are always looking for highly self-motivated students to work with us as PhD, master or visiting students. Please email us at xu.chen@ruc.edu.cn if you are interested in our team.
Recent Publications
2026
Know What You should not Know: Dynamic Attention Gating for Knowledge-Bounded Role-Playing
Zongsheng Wang, Bowen Wu, qun yu, Dengzhengwei, Qin Lin, Xu Chen, Baoxun Wang
Conference on Empirical Methods in Natural Language Processing (EMNLP)
Understanding Reliability in LLM-based Human Behavior Simulation
Pei Wang, Lei Wang, Yuanzi Li, Xu Chen
Conference on Empirical Methods in Natural Language Processing (EMNLP)
Need-Aware Multi-Objective Reinforcement Learning for Emotionally Intelligent LLM Agents
Xiaohe Bo, Xueyang Feng, Rui Li, Zihang Tian, Xu Chen, Quanyu Dai
Conference on Neural Information Processing Systems (NeurIPS)
From Local Skills to Long-Horizon Tasks: Progressive Skill Exploration for LLM Web Agents
Xueyang Feng, Xiaohe Bo, Xu Chen, Quanyu Dai, Feng Wen
Conference on Neural Information Processing Systems (NeurIPS)
Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
Ziheng Li, Zexu Sun, Jinman Zhao, Erxue Min, Yongcheng Zeng, Hui Wu, Hengyi Cai, Shuaiqiang Wang, Xu Chen, Zhi-Hong Deng, Dawei Yin
Conference on Neural Information Processing Systems (NeurIPS)
HAPS: Hierarchical LLM Routing with Joint Architecture and Parameter Search
Zihang Tian, Rui Li, Jingsen Zhang, Xiaohe Bo, Wei Huo, Xu Chen
Conference on Neural Information Processing Systems (NeurIPS)
Towards Unified Memory Adaptation for LLM Agents: Textual, Latent, and Parametric Pathways
Rui Li, Haoran Tan, Xiaohe Bo, Yiqun Chen, Meizhi Zhong, Xiaochi Wei, Yan Gao, YIWU, Yao Hu, Xu Chen
Conference on Neural Information Processing Systems (NeurIPS)
How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants
Xueyang Feng, Weinan Gan, Xu Chen, Quanyu Dai, Yong Liu
Conference on Neural Information Processing Systems (NeurIPS Dataset Track)
OneRank: Unified Transformer-Native Ranking Architecture for Multi-Task Recommendation
Jiakai Tang, Sunhao Dai, Kun Wang, Zhiluohan Guo, Yu Zhao, Cong Fu, Kangle Wu, Yabo Ni, Anxiang Zeng, Xu Chen, Jun Xu
ACM SIGKDD Conference on Knowledge Discovery and Data Mining Applied Data Science Track (KDD ADS)
Interactive Recommendation Agent with Active User Commands
Jiakai Tang, Wen Chen, Yujie Luo, XunkeXi, YI CHAO, Dian Chen, Zhujin Gao, Yang Li, Fei Sun, Xueyang Feng, Sunhao Dai, Xu Chen, Jian Wu, Yuning Jiang, Bo Zheng
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation
Jiakai Tang, Sunhao Dai, Teng Shi, Jun Xu, Xu Chen, Wen Chen, Jian Wu, Yuning Jiang
IEEE Transactions on Knowledge and Data Engineering (TKDE)
From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM Agents
Haoran Tan, Zeyu Zhang, Chen Ma, Tianze Liu, Quanyu Dai, Xu Chen
Annual Meeting of the Association for Computational Linguistics (ACL-findings)
Learning from Cognition: Enhancing RL Efficiency for LLM Reasoning via Hierarchical Metacognitive Decomposition and Refinement
Zexu Sun, Yongcheng Zeng, Erxue Min, Heyang Gao, Bokai Ji, Dugang Liu, Xing Tang, Xiuqiang He, Xu Chen
Annual Meeting of the Association for Computational Linguistics (ACL)
Divergence Meets Consensus: A Multi-Source Negative Sampling Framework for Sequential Recommendation
Yuanzi Li, Lingjie Wang, Jingyu Zhao, Zihang Tian, Yuhan Wang, Lei Wang, Xu Chen
International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)
Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents
Heyang Gao, Zexu Sun, Erxue Min, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Xu Chen
International Conference on Learning Representations (ICLR)
Prompt and Parameter Co-Optimization for Large Language Models
Xiaohe Bo, Rui Li, Zexu Sun, Quanyu Dai, Zeyu Zhang, Zihang Tian, Xu Chen, Zhenhua Dong
International Conference on Learning Representations (ICLR)
VeriRole: Verifiable Role-Awareness through Hint-Guided Reinforcement Learning
Zongsheng Wang, Kaili Sun, Bowen Wu, Qun Yu, Ying Li, Xu Chen, Baoxun Wang
International Conference on Learning Representations (ICLR)
CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs
Yongcheng Zeng, Zexu Sun, Bokai Ji, Erxue Min, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Haifeng Zhang, Xu Chen, Jun Wang
International Conference on Learning Representations (ICLR)
Optimizing Multi-Turn Interactive Recommendation Agents via Generative Intrinsic Motivation
Xueyang Feng, Jiakai Tang, Xu Chen, Quanyu Dai, Zhenhua Dong
The Web Conference (WWW)
Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information
Zeyu Zhang, Yang Zhang, Haoran Tan, Rui Li, Xu Chen
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)