4 papers
MASPrism: Lightweight Failure Attribution for Multi-Agent Systems Using Prefill-Stage Signals
Yang Liu, Hongjiang Feng, Junsong Pu +1
Failure attribution in LLM-based multi-agent systems aims to identify the steps that contribute to a failed execution. This task remains difficult because a single execution can co…
TypeScript Repository Indexing for Code Agent Retrieval
Junsong Pu, Yichen Li, Zhuangbin Chen
Graph-based code indexing can improve context retrieval for LLM-based code agents by preserving call chains and dependency relationships that keyword search and similarity retrieva…
ErrorPrism: Reconstructing Error Propagation Paths in Cloud Service Systems
Junsong Pu, Yichen Li, Zhuangbin Chen +6
Reliability management in cloud service systems is challenging due to the cascading effect of failures. Error wrapping, a practice prevalent in modern microservice development, enr…
Tracezip: Efficient Distributed Tracing via Trace Compression
Zhuangbin Chen, Junsong Pu, Zibin Zheng
Distributed tracing serves as a fundamental building block in the monitoring and testing of cloud service systems. To reduce computational and storage overheads, the de facto pract…