Junwu Xiong

Junwu Xiong

Auto-generated profile, based on publicly available information

Junwu Xiong

AI Infra Team at JD Technology,Beijing,China,100176

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
21 February 2025 in ACM Computing Surveys
Verified
Journal Article
Open access
ZDZehang Deng
Zehang Deng
YGYongjian Guo
Yongjian Guo
CHChangzhou Han
Changzhou Han
WMWanlun Ma
Wanlun Ma
JXJunwu Xiong
Junwu Xiong
YXYang Xiang
Yang Xiang
An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs. AI agents, capable of perceiving user inputs, reasoning and planning tasks, and executing actions, have seen remarkable advancements in algorithm development and task performance. However, the security challenges they pose remain under-explored and unresolved. This survey delves into the emerging security threats faced by AI agents, categorizing them into four critical knowledge gaps: unpredictability of multi-step user inputs, complexity in internal executions, variability of operational environments, and interactions with untrusted external entities. By systematically reviewing these threats, this article highlights both the progress made and the existing limitations in safeguarding AI agents. The insights provided aim to inspire further research into addressing the security threats associated with AI agents, thereby fostering the development of more robust and secure AI agent applications.

30 April 2026 in IEEE/CAA Journal of Automatica Sinica
Verified
Journal Article
Closed access
WMWanlun Ma
Wanlun Ma
YGYongjian Guo
Yongjian Guo
QHQing-Long Han
Qing-Long Han
WZWei Zhou
Wei Zhou
SZSean X. Zhu
Sean X. Zhu
YXYang Xiang
Yang Xiang
The rapid evolution of large language models (LLMs) towards autonomous Agentic artificial intelligence (AI) necessitates a systemic overhaul across algorithms, infrastructure, and architectures. This paper presents a unified view of the “Agentic AI Infrastructure,” connecting research threads often studied in isolation. First, post-training algorithms are reviewed, contrasting traditional reinforcement learning (RL) with emerging reasoning-centric methods and test-time scaling strategies. Next, the transition of RL training frameworks is analyzed from monolithic, colocated designs to disaggregated, asynchronous architectures tailored for the extreme variance of agentic rollouts. Furthermore, progress in agent construction is synthesized, covering reflection, planning, tool use, and multi-agent collaboration. By integrating these layers, the paper elucidates how agentic AI systems impose unique demands on underlying training systems. Finally, open challenges are outlined by covering capability scaling, efficiency, safety, privacy, and governance for reliable real-world agentic AI deployment.

12 March 2024 in IEEE Transactions on Emerging Topics in Computational Intelligence
Verified
Journal Article
Closed access
XTXiaoyu Tan
Xiaoyu Tan
CQChao Qu
Chao Qu
JXJunwu Xiong
Junwu Xiong
JZJames Zhang
James Zhang
XQXihe Qiu
Xihe Qiu
YJYaochu Jin
Yaochu Jin
Model-based reinforcement learning (MBRL) has shown its advantages in sample efficiency over model-free reinforcement learning (MFRL) by leveraging control-based domain knowledge. Despite the impressive results it achieves, MBRL is still outperformed by MFRL due to the lack of unlimited interactions with the environment. While imaginary data can be generated by imagining the trajectories of future states, a trade-off between the usage of data generation and the influence of model bias remains to be resolved. In this paper, we propose a simple and elegant off-policy model-based deep reinforcement learning algorithm with a model embedded in the framework of probabilistic reinforcement learning, called MEMB. To balance the sample-efficiency and model bias, we exploit both real and imaginary data in training. In particular, we embed the model in the policy update and learn value functions from the real data set. We also provide a theoretical analysis of MEMB with the Lipschitz continuity assumption on the model and policy, proving the reliability of the short-term imaginary rollout. Finally, we evaluate MEMB on several benchmarks and demonstrate that our algorithm can achieve state-of-the-art performance.

1 June 2026 in IEEE/CAA Journal of Automatica Sinica
Verified
Journal Article
Closed access
WMWanlun Ma
Wanlun Ma
QHQing-Long Han
Qing-Long Han
SZSean X. Zhu
Sean X. Zhu
WZWei Zhou
Wei Zhou
JXJunwu Xiong
Junwu Xiong
YXYang Xiang
Yang Xiang