4 citations · 11 across the 18 of their papers we have counts for
10 papers · 1 filter
Cascade Failure Attribution for Multi-Agent Systems
Jiayi Zhang, Zexin Wang, Degang Sun +4
Large language model (LLM)-based agents have shown strong potential in solving complex tasks through multi-step reasoning, yet they remain vulnerable to execution failures. Accurat…
LongRCA Bench: Root-Cause Localization in Long-Horizon Agent Trajectories
Yunfei Zhang, Boyu Feng, Changhua Pei +14
In long agent executions, an early error can persist through later actions and checks, while evidence needed to trace its origin is dispersed across the history. Short histories of…
Don't Predict, Prioritize: Rethinking GPU Reliability Assessment
Difeng Ma, Changhua Pei, Yuanwei Lu +7
The reliability of Graphics Processing Units (GPUs) is a criticalbottleneck for modern large-scale AI infrastructure, where a sin-gle node failure can disrupt synchronous training…
WeaveEarth: Structured Evidence Construction and Reasoning for Training-Free UHR Remote Sensing Understanding
Xianzhi Ma, Shujun Wang, Xiaohan Li +3
Ultra-High-Resolution (UHR) remote sensing image understanding requires Vision-Language Models (VLMs) to capture both the global scene layout and sparse yet task-critical local det…
A Multi-Dataset Benchmark for Evaluating LLM Agents in Microservice Failure Diagnosis
Yuanhong Cai, Xiaohui Nie, Kanglin Yin +8
LLM-based agents are reshaping microservice operations into AgentOps, where benchmarks are key to evaluating failure diagnosis over multimodal observability data. However, existing…
UModel: An Agent-Ready Observability Data Modeling Method at Scale
Changhua Pei, Zheyuan Li, Zexin Wang +10
When networked system failures occur, automatically performing Root Cause Analysis (RCA) using observability data is critical for ensuring networked system reliability. Recently, L…
Agent System Operations: Categorization, Challenges, and Future Directions
Zexin Wang, Changhua Pei, Yuanhao Liu +10
As the reasoning capabilities of Large Language Models (LLMs) continue to advance, LLM-based agent systems offer advantages in flexibility and interpretability over traditional sys…
LEC-KG: An LLM-Embedding Collaborative Framework for Domain-Specific Knowledge Graph Construction -- A Case Study on SDGs
Yikai Zeng, Yingchao Piao, Changhua Pei +1
Constructing domain-specific knowledge graphs from unstructured text remains challenging due to heterogeneous entity mentions, long-tail relation distributions, and the absence of…
KairosVL: Orchestrating Time Series and Semantics for Unified Reasoning
Haotian Si, Changhua Pei, Xiao He +9
Driven by the increasingly complex and decision-oriented demands of time series analysis, we introduce the Semantic-Conditional Time Series Reasoning task, which extends convention…
Strong Linear Baselines Strike Back: Closed-Form Linear Models as Gaussian Process Conditional Density Estimators for TSAD
Aleksandr Yugay, Hang Cui, Changhua Pei +1
Research in time series anomaly detection (TSAD) has largely focused on developing increasingly sophisticated, hard-to-train, and expensive-to-infer neural architectures. We revisi…