collaborators

13 papers

cs.RO2026

IcFuzz: Fuzzing Isaac Sim with Semantic Stage Guidance and Multi-level Mutation

Zhixiang Chen, Zhuangbin Chen, Ruoxi Jia +4

Robotics simulators serve as a foundational infrastructure for embodied AI, facilitating safe and scalable robotic system development. NVIDIA Isaac Sim has emerged as one of the mo…

cs.SE2026

LogNLQ: Natural-Language Log Querying with Parser-Induced and Semantically Grounded Schemas

Juepeng Wang, Jinyang Liu, Zhuangbin Chen +1

Logs are essential for system monitoring and failure diagnoses in modern software systems, yet querying them through natural language remains an open challenge. Existing approaches…

cs.SE2026

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…

cs.SE2026

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…

cs.SE2026

MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems

Jin Jia, Zhiling Deng, Zhuangbin Chen +2

As LLM-based Multi-Agent Systems (MAS) are increasingly deployed for complex tasks, ensuring their reliability has become a pressing challenge. Since MAS coordinate through unstruc…

cs.SE2026

LogPrism: Unifying Structure and Variable Encoding for Effective Log Compression

Yang Liu, Kaiming Zhang, Zhuangbin Chen +1

In the field of log compression, the prevailing "parse-then-compress" paradigm fundamentally limits effectiveness by treating log parsing and compression as isolated objectives. Wh…