activity
20242026
most citedFlow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysis

1 citations · 1 across the 9 of their papers we have counts for

collaborators

12 papers

cs.AI2026

Detect Before You Attribute: 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…

cs.AI2026

LongRCA Bench: Diagnosing Responsible Roles and Root Causes in Long-Horizon Agent Failures

Yunfei Zhang, Boyu Feng, Changhua Pei +14

When a long-horizon agent execution fails, outcome-level evaluation reveals the unsuccessful result but not where the decisive error entered the trajectory. Developers must then in…

cs.DC2026

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…

cs.SE2026

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…

cs.MA2026

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…

cs.AI2026

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…