3 papers
cs.AI2026
Reasoning Structure Matters for Safety Alignment of Reasoning Models
Yeonjun In, Wonjoong Kim, Sangwu Park +1
Large reasoning models (LRMs) achieve strong performance on complex reasoning tasks but often generate harmful responses to malicious user queries. This paper investigates the unde…
cs.AI2026
Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation
Yeonjun In, Mehrab Tanjim, Jayakumar Subramanian +6
Failure attribution is essential for diagnosing and improving multi-agent systems (MAS), yet existing benchmarks and methods largely assume a single deterministic root cause for ea…
cs.AI2025
R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge
Yeonjun In, Wonjoong Kim, Sangwu Park +1
Although large reasoning models (LRMs) have demonstrated impressive capabilities on complex tasks, recent studies reveal that these models frequently fulfill harmful user instructi…