Jie Ouyang

Jie Ouyang

Auto-generated profile, based on publicly available information

Jie Ouyang

State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 February 2026
Verified
Conference Paper
Open access
CJChuang Jiang
Chuang Jiang
MCMingyue Cheng
Mingyue Cheng
XTxiaoyu tao
xiaoyu tao
QMQingyang Mao
Qingyang Mao
JOJie Ouyang
Jie Ouyang
QLQi Liu
Qi Liu

10 November 2025
Verified
Conference Paper
Open access
SYShuo Yu
Shuo Yu
MCMingyue Cheng
Mingyue Cheng
QLQi Liu
Qi Liu
DWDaoyu Wang
Daoyu Wang
JYJiqian Yang
Jiqian Yang
ECEnhong Chen
Enhong Chen

21 October 2026 in ACM Transactions on Information Systems
Verified
Journal Article
Open access
MCMingyue Cheng
Mingyue Cheng
YLYucong Luo
Yucong Luo
JOJie Ouyang
Jie Ouyang
QLQi Liu
Qi Liu
HLHuijie Liu
Huijie Liu
ECEnhong Chen
Enhong Chen
Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models. RAG leverages external knowledge sources, such as documents, databases, or structured data, to improve model performance and generate more accurate and contextually relevant outputs. This survey aims to provide a comprehensive overview of RAG by examining its fundamental components, including retrieval mechanisms, generation processes, and the integration between the two. We discuss the key characteristics of RAG, such as its ability to augment generative models with dynamic external knowledge, and the challenges associated with aligning retrieved information with generative objectives. We also present a taxonomy that categorizes RAG methods, ranging from basic retrieval-augmented approaches to more advanced models incorporating multimodal data and reasoning capabilities. Additionally, we review the evaluation benchmarks and datasets commonly used to assess RAG systems, along with a detailed exploration of its applications in fields such as question answering, summarization, and information retrieval. Finally, we highlight emerging research directions and opportunities for improving RAG systems, such as enhanced retrieval efficiency, model interpretability, and domain-specific adaptations. This article concludes by outlining the prospects for RAG in addressing real-world challenges and its potential to drive further advancements in natural language processing ( https://github.com/USTCAGI/Awesome-Papers-Retrieval-Augmented-Generation ).

6 November 2026
Verified
Conference Paper
Open access
MCMingyue Cheng
Mingyue Cheng
SYShuo Yu
Shuo Yu
DWDaoyu Wang
Daoyu Wang
QLQingchuan Li
Qingchuan Li
XTxiaoyu tao
xiaoyu tao
ECEnhong Chen
Enhong Chen
LLM agents increasingly rely on reinforcement learning to improve multi-turn reasoning, tool use, and environment interaction. However, existing training pipelines often treat an agent trajectory as a flat token sequence or a reconstructed message trace, making it difficult to preserve rollout fidelity, manage long contexts, and inspect step-level credit signals. We present Agent-R1, an open-source modular framework for agentic reinforcement learning (RL). Agent-R1 uses interaction steps as the native unit for trajectory representation, replay, and environment interaction, and decouples exact trajectory storage from flexible context construction. The system supports context-management policies, step-level rollout inspection, action-mask visualization, tool-feedback analysis, and unified comparison of related RL algorithms. Through demonstrations on multiple tasks, Agent-R1 enables users to configure, train, inspect, and compare agentic RL workflows within a single interactive interface. Code and project resources are available at https://github.com/AgentR1/Agent-R1.