Peng Xu
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper formalizes TOCTOU vulnerabilities in GUI agents due to observation-to-action delays and proposes a layered defense, Pre-execution UI State Verification (PUSV), achieving high interception rates against various attacks.
This paper comparatively evaluates DKnownAI Guard against three competitors, demonstrating that DKnownAI Guard achieves superior performance in detecting both agent-specific threats and harmful content.
SkillC introduces a Contrastive Skill Credit Assignment (CSCA) framework to enable LLM agents to autonomously internalize skills during training, significantly outperforming existing methods without requiring runtime skill access.
Papers
SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit Assignment
SkillC introduces a Contrastive Skill Credit Assignment (CSCA) framework to enable LLM agents to autonomously internalize skills during training, significantly outperforming existing methods without r…