← Search

Rishi Rajesh Shah

2 accepted papers

2025

Dissecting Adversarial Robustness of Multimodal LM Agents

ICLR 2025poster

As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components taking actions, which existing LMs safety evaluations do not adequately address…