Wen Shen

MemMorph introduces a novel memory poisoning attack that biases LLM agent tool selection by injecting crafted records into the agent's long-term memory, achieving high success rates even against modern defenses.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.

The paper introduces PhoneWorld, a scalable pipeline that automatically converts real-world GUI trajectories and screenshots into controllable, reproducible phone-use environments, significantly improving agent performance across multiple mobile benchmarks.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.

The paper introduces HLL, a benchmark that tests if multimodal agents can successfully substitute for human verification (like CAPTCHA) in complex, real-world workflows, finding that current agents are still brittle and fail under realistic conditions.