Leyi Pan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Leyi Pan has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Lingzhe Zhang
Peking University, Beijing, China
4 shared publications - Chiming Duan
Peking University, Beijing, China
3 shared publications - Minghua He
Peking University, Beijing, China
3 shared publications - Tong Jia
Peking University, Beijing, China
3 shared publications - Yunpeng Zhai
Alibaba Group, Shanghai, Shanghai, China
3 shared publications - Aiwei Liu
Tsinghua University, Beijing, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7960-7968
Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7960-7968
Open AccessOmni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1295-1307
Bifrost: Empowering Pretrained Language Model with Fallibility Representation for Log-Based Fault Diagnosis
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1295-1307
Open AccessBifrost: Empowering Pretrained Language Model with Fallibility Representation for Log-Based Fault Diagnosis
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 58-69
Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microservices
As contemporary microservice systems become increasingly popular and complex—often comprising hundreds or even thousands of fine-grained, interdependent subsystems—they are experiencing more frequent failures. Ensuring system reliability thus demands accurate root cause localization. While many traditional graph-based and deep learning approaches have been explored for this task, they often rely heavily on pre-defined schemas that struggle to adapt to evolving operational contexts. Consequently, a number of LLM-based methods have recently been proposed. However, these methods still face two major limitations: shallow, symptom-centric reasoning that undermines accuracy, and a lack of cross-alert reuse that leads to redundant reasoning and high latency. In this paper, we conduct a comprehensive study of how Site Reliability Engineers (SREs) localize the root causes of failures, drawing insights from professionals across multiple organizations. Our investigation reveals that expert root cause analysis exhibits three key characteristics: recursiveness, multi-dimensional expansion, and cross-modal reasoning. Motivated by these findings, we introduce AMER-RCL, an agentic memory enhanced recursive reasoning framework for root cause localization in microservices. AMER-RCL employs the Recursive Reasoning RCL engine, a multi-agent framework that performs recursive reasoning on each alert to progressively refine candidate causes, while Agentic Memory incrementally accumulates and reuses reasoning from prior alerts within a time window to reduce redundant exploration and lower inference latency. Experimental results demonstrate that AMER-RCL consistently outperforms state-of-the-art methods in both localization accuracy and inference efficiency.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 58-69
Open AccessAgentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microservices
As contemporary microservice systems become increasingly popular and complex—often comprising hundreds or even thousands of fine-grained, interdependent subsystems—they are experiencing more frequent failures. Ensuring system reliability thus demands accurate root cause localization. While many traditional graph-based and deep learning approaches have been explored for this task, they often rely heavily on pre-defined schemas that struggle to adapt to evolving operational contexts. Consequently, a number of LLM-based methods have recently been proposed. However, these methods still face two major limitations: shallow, symptom-centric reasoning that undermines accuracy, and a lack of cross-alert reuse that leads to redundant reasoning and high latency. In this paper, we conduct a comprehensive study of how Site Reliability Engineers (SREs) localize the root causes of failures, drawing insights from professionals across multiple organizations. Our investigation reveals that expert root cause analysis exhibits three key characteristics: recursiveness, multi-dimensional expansion, and cross-modal reasoning. Motivated by these findings, we introduce AMER-RCL, an agentic memory enhanced recursive reasoning framework for root cause localization in microservices. AMER-RCL employs the Recursive Reasoning RCL engine, a multi-agent framework that performs recursive reasoning on each alert to progressively refine candidate causes, while Agentic Memory incrementally accumulates and reuses reasoning from prior alerts within a time window to reduce redundant exploration and lower inference latency. Experimental results demonstrate that AMER-RCL consistently outperforms state-of-the-art methods in both localization accuracy and inference efficiency.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 21-25
Hypothesize-Then-Verify: Speculative Root Cause Analysis for Microservices with Pathwise Parallelism
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 21-25
Open AccessHypothesize-Then-Verify: Speculative Root Cause Analysis for Microservices with Pathwise Parallelism
- Top Cited PapersOpen Access
- 7 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57 (2) , 1-36
A Survey of Text Watermarking in the Era of Large Language Models
Text watermarking algorithms are crucial for protecting the copyright of textual content. Historically, their capabilities and application scenarios were limited. However, recent advancements in large language models (LLMs) have revolutionized these techniques. LLMs not only enhance text watermarking algorithms with their advanced abilities but also create a need for employing these algorithms to protect their own copyrights or prevent potential misuse. This work conducts a comprehensive survey of the current state of text watermarking technology, covering four main aspects: (1) an overview and comparison of different text watermarking techniques; (2) evaluation methods for text watermarking algorithms, including their detectability, impact on text or LLM quality, and robustness under target or untargeted attacks; (3) potential application scenarios for text watermarking technology; and (4) current challenges and future directions for text watermarking. This survey aims to provide researchers with a thorough understanding of text watermarking technology in the era of LLMs, thereby promoting its further advancement.
- 7 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57 (2) , 1-36
Top Cited PapersOpen AccessA Survey of Text Watermarking in the Era of Large Language Models
Text watermarking algorithms are crucial for protecting the copyright of textual content. Historically, their capabilities and application scenarios were limited. However, recent advancements in large language models (LLMs) have revolutionized these techniques. LLMs not only enhance text watermarking algorithms with their advanced abilities but also create a need for employing these algorithms to protect their own copyrights or prevent potential misuse. This work conducts a comprehensive survey of the current state of text watermarking technology, covering four main aspects: (1) an overview and comparison of different text watermarking techniques; (2) evaluation methods for text watermarking algorithms, including their detectability, impact on text or LLM quality, and robustness under target or untargeted attacks; (3) potential application scenarios for text watermarking technology; and (4) current challenges and future directions for text watermarking. This survey aims to provide researchers with a thorough understanding of text watermarking technology in the era of LLMs, thereby promoting its further advancement.