6 papers
One Missing Piece for Open-Source Reasoning Models: A Dataset to Mitigate Cold-Starting Short CoT LLMs in RL
Hyungjoo Chae, Dongjin Kang, Jihyuk Kim +6
With the release of R1, a publicly available large reasoning model (LRM), researchers commonly train new LRMs by training language models on R1's long chain-of-thought (CoT) infere…
Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization
Sunghwan Kim, Dongjin Kang, Taeyoon Kwon +3
Reward models (RMs) play a crucial role in reinforcement learning from human feedback (RLHF), aligning model behavior with human preferences. However, existing benchmarks for rewar…
ToolHaystack: Stress-Testing Tool-Augmented Language Models in Realistic Long-Term Interactions
Beong-woo Kwak, Minju Kim, Dongha Lim +5
Large language models (LLMs) have demonstrated strong capabilities in using external tools to address user inquiries. However, most existing evaluations assume tool use in short co…
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…
Coffee-Gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code
Hyungjoo Chae, Taeyoon Kwon, Seungjun Moon +7
This paper presents Coffee-Gym, a comprehensive RL environment for training models that provide feedback on code editing. Coffee-Gym includes two major components: (1) Coffee, a da…
Evaluating Robustness of Reward Models for Mathematical Reasoning
Sunghwan Kim, Dongjin Kang, Taeyoon Kwon +4
Reward models are key in reinforcement learning from human feedback (RLHF) systems, aligning the model behavior with human preferences. Particularly in the math domain, there have…