14 papers
From Noise to Diversity: Random Embedding Injection in LLM Reasoning
Heejun Kim, Seungpil Lee, Jewon Yeom +5
Recent soft prompt research has tried to improve reasoning by inserting trained vectors into LLM inputs, yet whether the gain comes from the learned content or from the act of inje…
TRACED: Transition-aware Regret Approximation with Co-learnability for Environment Design
Geonwoo Cho, Jaegyun Im, Jihwan Lee +3
Generalizing deep reinforcement learning agents to unseen environments remains a significant challenge. One promising solution is Unsupervised Environment Design (UED), a co-evolut…
AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification
Geonwoo Cho, Jaemoon Lee, Jaegyun Im +3
Skill-based reinforcement learning (SBRL) enables rapid adaptation in environments with sparse rewards by pretraining a skill-conditioned policy. Effective skill learning requires…
ARCTraj: A Dataset and Benchmark of Human Reasoning Trajectories for Abstract Problem Solving
Sejin Kim, Hayan Choi, Seokki Lee +1
We present ARCTraj, a dataset and methodological framework for modeling human reasoning through complex visual tasks in the Abstraction and Reasoning Corpus (ARC). While ARC has in…
Can Large Language Models Develop Gambling Addiction?
Seungpil Lee, Donghyeon Shin, Yunjeong Lee +1
This study identifies the specific conditions under which large language models exhibit human-like gambling addiction patterns, providing critical insights into their decision-maki…
System 2 Reasoning for Human-AI Alignment: Generality and Adaptivity via ARC-AGI
Sejin Kim, Sundong Kim
Despite their broad applicability, transformer-based models still fall short in System~2 reasoning, lacking the generality and adaptivity needed for human--AI alignment. We examine…