2 papers
cs.CR2026
ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts
Yang Luo, Zifeng Kang, Tiantian Ji +4
Graph-based agent memory is increasingly used in LLM agents to support structured long-term recall and multi-hop reasoning, but it also creates a new poisoning surface: an attacker…
cs.CL2026
Proactive Dialogue Model with Intent Prediction
Yang Luo
Dialogue models are inherently reactive, responding to the current user turn without anticipating upcoming intents, which leads to redundant interactions in multi-intent settings.…