Chenxi Wang

This paper introduces a latent attack framework demonstrating that attacks can be embedded into the hidden representations of multi-agent systems, causing performance degradation even during clean, non-adversarial executions.

The paper introduces AbaqusAgent, a multi-AI-agent framework that uses large language models to translate natural language instructions into executable Finite Element Analysis (FEA) simulations using Abaqus.

SkillAdaptor is a novel, training-free framework that enables stable, step-level adaptation of external skills for LLM agents by precisely attributing failures to specific skills.