activity
20232026
most citedRetrieval-Augmented Generation for Large Language Models: A Survey

747 citations · 747 across the 9 of their papers we have counts for

collaborators
Showing cs.CRShow all

7 papers · 1 filter

cs.CR2026

Transferable End-to-End Optimization for Indirect Long-Term Memory Poisoning in LLM Agents

Chuanchao Zang, Jianing Wang, Wenyu Chen +5

Long-term memory can turn untrusted external content into persistent influence over an LLM agent's future decisions, creating the threat of indirect memory poisoning. A successful…

cs.CR2026

Understanding and Exploiting Initialization Anchoring Weakness in Feedback-Based Agent Planning

Chuanchao Zang, Jianing Wang, Wenyu Chen +6

Feedback-based planning improves agent reliability by incorporating tool observations and corrective feedback. However, its protection may not be distributed uniformly across plann…

cs.CR2026

Extracting Knowledge from Tools in LLM Agents

Chuanchao Zang, Jianing Wang, Wenyu Chen +6

LLM agents commonly use knowledge-based tools and access their underlying files, databases, and search indexes through tool invocation. This integration improves agents' ability to…

cs.CR2026

Understanding Stage-Wise Utility-Risk Trade-offs in LLM Agent Memory

Chuanchao Zang, Zijian Cao, Xiangtao Meng +6

Long-term memory is becoming a core capability of LLM agents, enabling personalization and long-horizon interaction. However, memory mechanisms that retain, transform, or expose mo…

cs.CR2026

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents

Xinyu Gao, Wenyu Chen, Xiangtao Meng +5

LLM-based agents extend large language models with long-term memory (LTM) that persists privacy-sensitive user data across sessions. Production systems mitigate extraction risks th…

cs.CR2026

Defenses at Odds: Measuring and Explaining Defense Conflicts in Large Language Models

Xiangtao Meng, Wenyu Chen, Chuanchao Zang +5

Large Language Models (LLMs) deployed in high-stakes applications must simultaneously manage multiple risks, yet existing defenses are almost exclusively evaluated in isolation und…