activity
20242026
collaborators

6 papers

cs.MA2026

ASCon: A Direction-Aware Reciprocal Agent--Step Contextualization Model for Failure Attribution in Multi-Agent Systems

Shuyu Jiang, Yue Ran, Kaiyu Xu +5

Failure attribution in LLM-based multi-agent systems (MAS) aims to answer who caused failures, when they occurred, and why by identifying responsible targets including faulty agent…

cs.CL2026

One Jailbreak, Many Tongues: Learning Language-Insensitive Intention Representations for Multilingual Jailbreak Detection

Shuyu Jiang, Kaiyu Xu, Xingshu Chen +5

Large language models (LLMs) are increasingly deployed in applications for global multilingual users, yet safety training remains concentrated in dominant languages and has not pro…

cs.NE2026

EvoJail: Evolutionary Diverse Jailbreak Prompt Generation for Large Language Models

Rui Tang, Kaiyu Xu, Pengsen Cheng +3

As LLMs continue to shape real-world applications, automated jailbreak generation becomes essential to reveal safety weaknesses and guide model improvement. Existing automatic jail…

physics.soc-ph2026

Large language models for spreading dynamics in complex systems

Shuyu Jiang, Hao Ren, Yichang Gao +6

Spreading dynamics is a central topic in the physics of complex systems and network science, providing a unified framework for understanding how information, behaviors, and disease…

physics.soc-ph2025

Network Alignment

Rui Tang, Ziyun Yong, Shuyu Jiang +5

Complex networks are frequently employed to model physical or virtual complex systems. When certain entities exist across multiple systems simultaneously, unveiling their correspon…

cs.CL2024

ReZG: Retrieval-Augmented Zero-Shot Counter Narrative Generation for Hate Speech

Shuyu Jiang, Wenyi Tang, Xingshu Chen +3

The proliferation of hate speech (HS) on social media poses a serious threat to societal security. Automatic counter narrative (CN) generation, as an active strategy for HS interve…