6 papers
AgentChaos: Chaos Engineering for Agent Systems via Programmatic Fault Injection
Gou Tan, Zhensu Sun, Jieke Shi +10
Agent systems rely on LLM APIs for every response, but these APIs can return server errors, truncated responses, or corrupted content that propagates through downstream agents and…
LIDL: LLM Integration Defect Localization via Knowledge Graph-Enhanced Multi-Agent Analysis
Gou Tan, Zilong He, Min Li +8
LLM-integrated software, which embeds or interacts with large language models (LLMs) as functional components, exhibits probabilistic and context-dependent behaviors that fundament…
InferLog: Accelerating LLM Inference for Online Log Parsing via ICL-oriented Prefix Caching
Yilun Wang, Pengfei Chen, Haiyu Huang +5
Modern software systems generate massive volumes of runtime logs, necessitating efficient and accurate log parsing to enable critical downstream tasks such as anomaly detection and…
DaiFu: In-Situ Crash Recovery for Deep Learning Systems
Zilong He, Pengfei Chen, Hongyu Zhang +4
Deep learning (DL) systems have been widely adopted in many areas, and are becoming even more popular with the emergence of large language models. However, due to the complex softw…
FaaSRCA: Full Lifecycle Root Cause Analysis for Serverless Applications
Jin Huang, Pengfei Chen, Guangba Yu +3
Serverless becomes popular as a novel computing paradigms for cloud native services. However, the complexity and dynamic nature of serverless applications present significant chall…
Mint: Cost-Efficient Tracing with All Requests Collection via Commonality and Variability Analysis
Haiyu Huang, Cheng Chen, Kunyi Chen +6
Distributed traces contain valuable information but are often massive in volume, posing a core challenge in tracing framework design: balancing the tradeoff between preserving esse…