3 papers
cs.CR2026
Your Agentic LLMs Secretly Encode Indirect Prompt-Injection Exposure in Hidden States
Jianshuo Dong, Yiming Liu, Maosen Zhang +7
Agentic LLMs are vulnerable to indirect prompt injection (IPI) attacks, e.g., malicious side-tasks hidden in external tool results. While many efforts have sought to address this t…
cs.CR2026
LeakDojo: Decoding the Leakage Threats of RAG Systems
Maosen Zhang, Jianshuo Dong, Boting Lu +4
Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to leverage external knowledge, but also exposes valuable RAG databases to leakage attacks. As RAG systems…
cs.CL2026
AlphaResearch: Accelerating New Algorithm Discovery with Language Models
Zhaojian Yu, Kaiyue Feng, Yilun Zhao +3
LLMs have made significant progress in complex but easy-to-verify problems, yet they still struggle with discovering the unknown. In this paper, we present \textbf{AlphaResearch},…