5 papers
Rollout-Level Advantage-Prioritized Experience Replay for GRPO
Gyeongtae Yoo, Sanghyeok Park, Soohyuk Jang +2
Reinforcement learning from verifiable rewards with GRPO is a standard approach for post-training reasoning LLMs. It remains sample inefficient. Each rollout is used for a single g…
Knowledge Integration Decay in Search-Augmented Reasoning of Large Language Models
Sangwon Yu, Ik-hwan Kim, Donghun Kang +6
Modern Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks by employing search-augmented reasoning to incorporate external knowledge into long c…
Distilling Metacognitive Behaviors through Agentic Editing
Ik-hwan Kim, Hyeongrok Han, Mingi Jung +5
Distilling long reasoning traces from a teacher model into a smaller student also passes on the teacher's reasoning habits. Prior work and our annotation of teacher traces show tha…
Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis
Jisoo Mok, Ik-hwan Kim, Sangkwon Park +1
Personalized AI assistants, a hallmark of the human-like capabilities of Large Language Models (LLMs), are a challenging application that intertwines multiple problems in LLM resea…
Unleashing Multi-Hop Reasoning Potential in Large Language Models through Repetition of Misordered Context
Sangwon Yu, Ik-hwan Kim, Jongyoon Song +3
Multi-hop reasoning, which requires multi-step reasoning based on the supporting documents within a given context, remains challenging for large language models (LLMs). LLMs often…