Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
publications
Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications
Published in arXiv preprint, 2024
Feedback-guided extraction of knowledge bases from retrieval-augmented LLM applications.
Recommended citation: Changyue Jiang et al. (2024). "Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications." arXiv preprint.
Download Paper
Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction
Published in ICML 2026, 2026
Enhancing agent behavioral safety through thought correction.
Recommended citation: Changyue Jiang et al. (2026). "Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction." ICML 2026.
Download Paper
MATE: Policy-Aware Security Auditing for Mobile Agents via Synthesis-Driven Trajectory Learning
Published in USENIX Security 2026, 2026
Policy-aware security auditing for mobile agents via synthesis-driven trajectory learning.
Recommended citation: Changyue Jiang et al. (2026). "MATE: Policy-Aware Security Auditing for Mobile Agents via Synthesis-Driven Trajectory Learning." USENIX Security 2026.
Download Paper
MirrorGuard: Toward Secure Computer-Use Agents via Simulation-to-Real Reasoning Correction
Published in ACM CCS 2026, 2026
Simulation-to-real reasoning correction for secure computer-use agents.
Recommended citation: Changyue Jiang et al. (2026). "MirrorGuard: Toward Secure Computer-Use Agents via Simulation-to-Real Reasoning Correction." ACM CCS 2026.
Download Paper