Showing cs.CRShow all
3 papers · 1 filter
cs.CR2026
: Improving Agent Safety through Multi-Stage Defense
Zibo Xiao, Haoyu Wang, Jun Sun
Large Language Model (LLM) agents rely on multi-stage agentic workflows, with stages such as memory, planning, and tool execution, to accomplish complex tasks. However, risks may e…
cs.CR2026
TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing for Jailbreaking and Red Teaming LLMs
Qingchao Shen, Zibo Xiao, Lili Huang +3
Large Language Models (LLMs) are increasingly deployed across diverse domains, yet their vulnerability to jailbreak attacks, where adversarial inputs bypass safety mechanisms to el…
cs.CR2026
SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants
Haoyu Wang, Zibo Xiao, Yedi Zhang +2
LLM-based multi-agent systems (MASs) are transforming personal productivity by autonomously executing complex, cross-platform tasks. Frameworks such as OpenClaw demonstrate the pot…