Sung Ju Hwang

The paper introduces T-MAP, a trajectory-aware evolutionary search method, to discover and generate multi-step adversarial prompts that exploit vulnerabilities in autonomous LLM agents through tool execution, significantly improving attack realization rates.

The paper proposes SELFCI, a complementary self-distillation framework that effectively balances the privacy requirements of Contextual Integrity (CI) with the utility of large language models, outperforming existing methods without external supervision.

The paper introduces LearnWeak, an annotation-free framework that automatically specializes small computer-use agents by identifying and targeting their specific weaknesses using a stronger reference agent, achieving significant performance gains on OSWorld.

OmniRetrieval introduces a unified framework that handles natural language queries across diverse, heterogeneous knowledge sources (text, relational, graphs) by dispatching source-native queries without homogenizing the data structure.