Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
MNC: Scope-Bound Semantic Declassification for Private LLM-Agent Communication
Jinghan Xu, Longze Fan, Zeyuan Wang +2
Multi-agent large language model (LLM) systems can expose protected state through internal messages, tool arguments, logs, and persistent memory even when their public outputs appe…
cs.CR2026
Policy-Backed Selective Regeneration under Tainted Inter-Agent Communication
Jinghan Xu, Longze Fan, Zeyuan Wang +2
Inter-agent communication is essential to multi-agent language-model systems, yet a single message may combine task-critical information with instructions not authorized by the ori…