9 papers
Blocking at the Boundary: Auditing Long-Horizon Agents against Staged Prompt Injection
Jingkai Liu, Yufei Han, Xiaoting Lyu +2
Long-horizon agents consume external content, invoke tools, and modify persistent state. Indirect prompt injection can exploit task-specific context, propagate across causally conn…
The Marathon of Scientific Reasoning: Robustness of Scientific Agents to Perturbations in Multi-Turn Interactions
Xiaoting Lyu, Xinbo Ma, Yufei Han +4
Large language model (LLM)-based scientific agents are increasingly used for scientific problem solving, yet their robustness to imperfections arising during multi-turn interaction…
AgentLeak: Cloning Stronger LLM Agent Capabilities onto Weaker Agents Beyond Skill Stealing
Xiaoting Lyu, Yuhong Wu, Yufei Han +5
Large language model (LLM) agents increasingly achieve long-horizon tasks by combining foundation models with explicit skills and implicit procedural knowledge acquired through exe…
Kwai Keye-VL-2.0 Technical Report
Kwai Keye Team, Bin Wen, Changyi Liu +50
We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding and agentic intelligence. To…
3SPO: State-Score-Supervised Policy Optimization for LLM Agents
Yu Han, Kailing Li, Yang Jiao +4
Training large language models (LLMs) as autonomous agents via reinforcement learning (RL) has enabled frontier models to achieve superhuman performance in long-horizon tasks. Howe…
AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills
Haomin Zhuang, Hanwen Xing, Yujun Zhou +5
Third-party skills are becoming the package ecosystem for LLM agents. They package natural-language instructions, helper scripts, templates, documents, and service configuration in…
BadSKP: Backdoor Attacks on Knowledge Graph-Enhanced LLMs with Soft Prompts
Xiaoting Lyu, Yufei Han, Hangwei Qian +6
Recent knowledge graph (KG)-enhanced large language models (LLMs) move beyond purely textual knowledge augmentation by encoding retrieved subgraphs into continuous soft prompts via…
Persistent Backdoor Attacks under Continual Fine-Tuning of LLMs
Jing Cui, Yufei Han, Jianbin Jiao +1
Backdoor attacks embed malicious behaviors into Large Language Models (LLMs), enabling adversaries to trigger harmful outputs or bypass safety controls. However, the persistence of…
BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning
Jing Cui, Yufei Han, Yuzhe Ma +2
Backdoor attacks in reinforcement learning (RL) have previously employed intense attack strategies to ensure attack success. However, these methods suffer from high attack costs an…