Aoxiao Zhong

Aoxiao Zhong

Auto-generated profile, based on publicly available information

Aoxiao Zhong

Havard Univerrsity, Cambridge, USA

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
15 September 2021 in Nature Medicine
Verified
Journal Article
Closed access
PDF file
IDIttai Dayan
Ittai Dayan
HRHolger Roth
Holger Roth
AZAoxiao Zhong
Aoxiao Zhong
AHAhmed Harouni
Ahmed Harouni
AGAmilcare Gentili
Amilcare Gentili
QLQuanzheng Li
Quanzheng Li

23 August 2024 in Medical Image Analysis
Verified
Journal Article
Closed access
CCCheng Chen
Cheng Chen
JMJuzheng Miao
Juzheng Miao
DWDufan Wu
Dufan Wu
AZAoxiao Zhong
Aoxiao Zhong
ZYZhiling Yan
Zhiling Yan
Quanzheng LiQuanzheng Li
Quanzheng Li

21 October 2024
Verified
Conference Paper
Open access
ZWZefan Wang
Zefan Wang
ZLZichuan Liu
Zichuan Liu
YZYingying Zhang
Yingying Zhang
AZAoxiao Zhong
Aoxiao Zhong
JWJi-Hong Wang
Ji-Hong Wang
QWQingsong Wen
Qingsong Wen
Large language model (LLM) applications in cloud root cause analysis (RCA) have been actively explored recently. However, current methods are still reliant on manual workflow settings and do not unleash LLMs' decision-making and environment interaction capabilities. We present RCAgent, a tool-augmented LLM autonomous agent framework for practical and privacy-aware industrial RCA usage. Running on an internally deployed model rather than GPT families, RCAgent is capable of free-form data collection and comprehensive analysis with tools. Our framework combines a variety of enhancements, including a unique Self-Consistency for action trajectories, and a suite of methods for context management, stabilization, and importing domain knowledge. Our experiments show RCAgent's evident and consistent superiority over ReAct across all aspects of RCA--predicting root causes, solutions, evidence, and responsibilities--and tasks covered or uncovered by current rules, as validated by both automated metrics and human evaluations. Furthermore, RCAgent has already been integrated into the diagnosis and issue discovery workflow of the Real-time Compute Platform for Apache Flink of Alibaba Cloud.

1 May 2021 in Medical Image Analysis
Verified
Journal Article
Closed access
AZAoxiao Zhong
Aoxiao Zhong
XLXiang Li
Xiang Li
DWDufan Wu
Dufan Wu
HRHui Ren
Hui Ren
KKKyungsang Kim
Kyungsang Kim
Quanzheng LiQuanzheng Li
Quanzheng Li

24 August 2024
Verified
Conference Paper
Open access
AZAoxiao Zhong
Aoxiao Zhong
DMDengyao Mo
Dengyao Mo
GLGuiyang Liu
Guiyang Liu
JLJinbu Liu
Jinbu Liu
QLQingda Lu
Qingda Lu
QWQingsong Wen
Qingsong Wen
Logs are ubiquitous digital footprints, playing an indispensable role in system diagnostics, security analysis, and performance optimization. The extraction of actionable insights from logs is critically dependent on the log parsing process, which converts raw logs into structured formats for downstream analysis. Yet, the complexities of contemporary systems and the dynamic nature of logs pose significant challenges to existing automatic parsing techniques. The emergence of Large Language Models (LLM) offers new horizons. With their expansive knowledge and contextual prowess, LLMs have been transformative across diverse applications. Building on this, we introduce LogParser-LLM, a novel log parser integrated with LLM capabilities. This union seamlessly blends semantic insights with statistical nuances, obviating the need for hyper-parameter tuning and labeled training data, while ensuring rapid adaptability through online parsing. Further deepening our exploration, we address the intricate challenge of parsing granularity, proposing a new metric and integrating human interactions to allow users to calibrate granularity to their specific needs. Our method's efficacy is empirically demonstrated through evaluations on the Loghub-2k and the large-scale LogPub benchmark. In evaluations on the LogPub benchmark, involving an average of 3.6 million logs per dataset across 14 datasets, our LogParser-LLM requires only 272.5 LLM invocations on average, achieving a 90.6% F1 score for grouping accuracy and an 81.1% for parsing accuracy. These results demonstrate the method's high efficiency and accuracy, outperforming current state-of-the-art log parsers, including pattern-based, neural network-based, and existing LLM-enhanced approaches.