1 citations · 1 across the 4 of their papers we have counts for
3 papers · 1 filter
Agents, Think Only When it Helps
Min-Seon Kim, Seungdong Yoa, Sanghyu Yoon +4
LLM agent distillation transfers agentic capabilities to student models by training on complete teacher trajectories that typically interleave thoughts and actions. We question how…
Efficient Multi-Agent Reasoning via Confidence-Guided Adaptive Debate
Seungdong Yoa, Ye Seul Sim, Suhee Yoon +5
Multi-agent debate has shown promise for improving the reasoning of large language models, yet recent theory suggests its benefits are highly regime-dependent. While interaction ca…
From Static Benchmarks to Dynamic Protocol: Agent-Centric Text Anomaly Detection for Evaluating LLM Reasoning
Seungdong Yoa, Sanghyu Yoon, Suhee Yoon +4
The evaluation of large language models (LLMs) has predominantly relied on static datasets, which offer limited scalability and fail to capture the evolving reasoning capabilities…