Qi Guo

The paper introduces LinuxArena, a large-scale, diverse control setting for testing AI agents in live production environments, demonstrating its utility for evaluating both attack and defense mechanisms.

The paper introduces MIRAGE, a novel pipeline that generates context-aware prompt injection attacks by injecting malicious text into user-generated content regions of mobile screenshots, successfully demonstrating the vulnerability of current GUI agents.

The paper introduces MIRAGE, a novel pipeline that generates context-aware prompt injection attacks by embedding malicious text into user-generated content regions of mobile screenshots, successfully demonstrating the vulnerability of current VLM-driven GUI agents.

The paper introduces SURE, a unified framework designed to standardize and improve the comparability and reproducibility of evaluations for advanced speech understanding models.

The paper introduces 3DCodeBench, a systematic benchmark and platform for evaluating Vision-Language Model (VLM) agents' ability to generate procedural 3D models from text and images using code.

The paper proposes Skill-RM, a unified framework that treats reward modeling as an agentic task to consistently integrate diverse evaluation criteria, achieving superior performance over traditional methods.

The paper proposes a novel Bayesian framework to learn the optimal decision strategy for the stochastic shortest path problem by directly constructing the posterior beliefs for the action-value function $Q^*$ using Bellman's optimality equations.