Rongkai Zhang

Rongkai Zhang

Auto-generated profile, based on publicly available information

Rongkai Zhang

School of Computer Science, Peking University, Beijing, China

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
24 August 2024
Verified
Conference Paper
Open access
MXMingzhe Xing
Mingzhe Xing
RZRongkai Zhang
Rongkai Zhang
HXHui Xue
Hui Xue
QCQi Chen
Qi Chen
FYFan Yang
Fan Yang
ZXZhen Xiao
Zhen Xiao
Large language models (LLMs) have empowered intelligent agents to execute intricate tasks within domain-specific software such as browsers and games. However, when applied to general-purpose software systems like operating systems, LLM agents face three primary challenges. Firstly, the action space is vast and dynamic, posing difficulties for LLM agents to maintain an up-to-date understanding and deliver accurate responses. Secondly, real-world tasks often require inter-application cooperation, demanding farsighted planning from LLM agents. Thirdly, agents need to identify optimal solutions aligning with user constraints, such as security concerns and preferences. These challenges motivate AndroidArena, an environment and benchmark designed to evaluate LLM agents on a modern operating system. To address high-cost of manpower, we design a scalable and semi-automated method to construct the benchmark. In the task evaluation, AndroidArena incorporates accurate and adaptive metrics to address the issue of non-unique solutions. Our findings reveal that even state-of-the-art LLM agents struggle in cross-APP scenarios and adhering to specific constraints. Additionally, we identify a lack of four key capabilities, i.e. understanding, reasoning, exploration, and reflection, as primary reasons for the failure of LLM agents. Furthermore, we provide empirical analysis on the failure of reflection, and improve the success rate by 27% with our proposed exploration strategy. This work is the first to present valuable insights in understanding fine-grained weakness of LLM agents, and offers a path forward for future research in this area. Environment, benchmark, prompt, and evaluation code for AndroidArena are released at https://github.com/AndroidArenaAgent/AndroidArena.

30 March 2025
Verified
Conference Paper
Open access
LPLichen Pan
Lichen Pan
JLJuncheng Liu
Juncheng Liu
YFYongquan Fu
Yongquan Fu
JYJinhui Yuan
Jinhui Yuan
RZRongkai Zhang
Rongkai Zhang
ZXZhen Xiao
Zhen Xiao

27 January 2026 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
SGShengjie Guan
Shengjie Guan
RZRongkai Zhang
Rongkai Zhang
QDQiuyu Ding
Qiuyu Ding
MSMingxuan Song
Mingxuan Song
ZXZhen Xiao
Zhen Xiao
JDJin Dong
Jin Dong
The transaction execution layer is a key determinant of throughput in permissioned blockchains. While recent Shared Memory Pools (SMP)-based approaches improve throughput by enabling all consensus nodes to participate in transaction packaging, they face two fundamental limitations. First, the performance bottleneck shifts from the consensus layer to the transaction execution layer as transaction number confirmed in a round increases. Second, these approaches are vulnerable to “transaction duplication” attacks where malicious clients can simultaneously send the same transaction to multiple consensus nodes, thereby decreasing the number of valid transactions in block proposals. To address these limitations, this paper introduces Nexus, a novel blockchain transaction processing framework with high scalability. Nexus leverages the idle computational resources of full nodes to enable transaction execution in parallel with the consensus. Moreover, Nexus allows each node to handle only a fraction of the total transactions and share execution results with others. This approach reduces overall transaction execution time, increases throughput, and decreases latency. Lastly, Nexus introduces a transaction partitioning mechanism that effectively addresses the “transaction duplication” attack and achieves load balancing between clients and consensus nodes. Our implementation of Nexus demonstrates significant improvements: throughput increases by 4x to 15x, and latency is reduced by 50% to 70%.

12 April 2026
Verified
Conference Paper
Open access
QDQiuyu Ding
Qiuyu Ding
RZRongkai Zhang
Rongkai Zhang
QZQinnan Zhang
Qinnan Zhang
ZXZhen Xiao
Zhen Xiao
JLJieyi Long
Jieyi Long
JDJin Dong
Jin Dong

11 November 2026 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
RZRongkai Zhang
Rongkai Zhang
QDQiuyu Ding
Qiuyu Ding
QLQianyi Liu
Qianyi Liu
SGShengjie Guan
Shengjie Guan
JSJing Shi
Jing Shi
JDJin Dong
Jin Dong