4 citations · 5 across the 7 of their papers we have counts for
7 papers
Experience Memory Graph: Extracting Reusable Correction Knowledge from Agent Trajectories
Wenjun Wang, Yuchen Fang, Fengrui Liu +2
Large Language Model (LLM) agents have shown remarkable capabilities in autonomous decision-making by generating sequential trajectories of states, actions, and observations. Howev…
Help Without Being Asked: A Deployed Proactive Agent System for On-Call Support with Continuous Self-Improvement
Fengrui Liu, Xiao He, Tieying Zhang
In large-scale cloud service platforms, thousands of customer tickets are generated daily and are typically handled through on-call dialogues. This high volume of on-call interacti…
CASTLE: A Comprehensive Benchmark for Evaluating Student-Tailored Personalized Safety in Large Language Models
Rui Jia, Ruiyi Lan, Fengrui Liu +7
Large language models (LLMs) have advanced the development of personalized learning in education. However, their inherent generation mechanisms often produce homogeneous responses…
SMRC: Aligning Large Language Models with Student Reasoning for Mathematical Error Correction
Biaojie Zeng, Min Zhang, Juan Zhou +4
Large language models (LLMs) often make reasoning errors when solving mathematical problems, and how to automatically detect and correct these errors has become an important resear…
EduAgentQG: Multi-Agent Personalized Mathematics Question Generation with Explicit Diversity and Objective-Aware Evaluation
Rui Jia, Min Zhang, Fengrui Liu +3
In intelligent education, personalized mathematics question generation aims to produce mathematics questions that satisfy educational requirements while supporting adaptive assessm…
TickIt: Leveraging Large Language Models for Automated Ticket Escalation
Fengrui Liu, Xiao He, Tieying Zhang +6
In large-scale cloud service systems, support tickets serve as a critical mechanism for resolving customer issues and maintaining service quality. However, traditional manual ticke…
Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysis
Changhua Pei, Zexin Wang, Fengrui Liu +9
In the realm of microservices architecture, the occurrence of frequent incidents necessitates the employment of Root Cause Analysis (RCA) for swift issue resolution. It is common t…