2 citations · 2 across the 5 of their papers we have counts for
8 papers
Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating Transfer
Minju Gwak, Alan Ritter
Answer-level rewards cannot distinguish reasoning traces with equally correct outcomes. We study whether auxiliary trajectory preferences improve small-language-model self-improvem…
ResearchMath-14K: Scaling Research-Level Mathematics via Agents
Guijin Son, Seungyeop Yi, Minju Gwak +3
The frontier of mathematics is defined by problems whose solutions are not yet known. However, whether language models can meaningfully engage with such problems without human inte…
LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training
Minju Gwak, Minseo Kwak, Dongseok Lee +3
Reinforcement learning (RL) post-training has shown to improve reasoning in large language models (LLMs). However, there has been little exploration on the problem of data contamin…
Revisiting the UID Hypothesis in LLM Reasoning Traces
Minju Gwak, Guijin Son, Jaehyung Kim
Large language models (LLMs) often solve problems using step-by-step Chain-of-Thought (CoT) reasoning, yet these intermediate steps are frequently unfaithful or hard to interpret.…
Revisiting the Uniform Information Density Hypothesis in LLM Reasoning
Minju Gwak, Guijin Son, Jaehyung Kim
The Uniform Information Density (UID) hypothesis proposes that effective communication is achieved by maintaining a stable flow of information. In this work, we revisit this princi…
Can You Share Your Story? Modeling Clients' Metacognition and Openness for LLM Therapist Evaluation
Minju Kim, Dongje Yoo, Yeonjun Hwang +11
Understanding clients' thoughts and beliefs is fundamental in counseling, yet current evaluations of LLM therapists often fail to assess this ability. Existing evaluation methods r…
Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
Hyungjoo Chae, Sunghwan Kim, Junhee Cho +18
Web navigation is a unique domain that can automate many repetitive real-life tasks and is challenging as it requires long-horizon sequential decision making beyond typical multimo…
Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation
Hyungjoo Chae, Namyoung Kim, Kai Tzu-iunn Ong +6
Large language models (LLMs) have recently gained much attention in building autonomous agents. However, the performance of current LLM-based web agents in long-horizon tasks is fa…