Agentic AI Alignment

Agentic AI systems act autonomously over long horizons, making alignment increasingly critical and challenging. We develop principled methods to ensure these agents remain truthful, safe, and secure — aligned with human intent throughout deployment.

How do we build AI agents that remain trustworthy as they act in the open world?

Keywords

  • Agentic AI
  • AI Alignment
  • Reinforcement Learning

3 Related Publications

Can We Stop Malicious AI? KILLBENCH: A Benchmark for External AI Kill Switch Feasibility
Sechan Lee, Hyounghun Kim, Sangdon Park
2026
The Interplay of Harness Design and Post-Training in LLM Agents
Kyungmin Kim*, Youngbin Choi*, Seoyeon Lee, Suhyeon Jun, Dongwoo Kim^, Sangdon Park^
International Conference on Machine Learning Workshop (ICML RLxF Workshop), 2026
ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System
Taesoo Kim, HyungSeok Han, Soyeon Park, Dae R. Jeong, Dohyeok Kim, Dongkwan Kim, Eunsoo Kim, Jiho Kim, Joshua Wang, Kangsu Kim, Sangwoo Ji, Woosun Song, Hanqing Zhao, Andrew Chin, Gyejin Lee, Kevin Stevens, Mansour Alharthi, Yizhuo Zhai, Cen Zhang, Joonun Jang, Yeongjin Jang, Ammar Askar, Dongju Kim, Fabian Fleischer, Jeongin Cho, Junsik Kim, Kyungjoon Ko, Insu Yun, Sangdon Park, Dowoo Baik, Haein Lee, Hyeon Heo, Minjae Gwon, Minjae Lee, Minwoo Baek, Seunggi Min, Wonyoung Kim, Yonghwi Jin, Younggi Park, Yunjae Choi, Jinho Jung, Gwanhyun Lee, Junyoung Jang, Kyuheon Kim, Yeonghyeon Cha, Youngjoon Kim
2025
🏆 DARPA AIxCC Winner - $(4+2)M Award