11 papers
Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy
Chris Yuhao Liu, Liang Zeng, Yuzhen Xiao +9
Despite the critical role of reward models (RMs) in Reinforcement Learning from Human Feedback (RLHF), current state-of-the-art open RMs perform poorly on most existing evaluation…
Incentivizing LLMs to Self-Verify Their Answers
Fuxiang Zhang, Jiacheng Xu, Chaojie Wang +3
Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks through both post-training and test-time scaling laws. While prevalent test-time scali…
Skywork Open Reasoner 1 Technical Report
Jujie He, Jiacai Liu, Chris Yuhao Liu +14
The success of DeepSeek-R1 underscores the significant role of reinforcement learning (RL) in enhancing the reasoning capabilities of large language models (LLMs). In this work, we…
Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization
Jiacai Liu, Chaojie Wang, Chris Yuhao Liu +5
The role of reinforcement learning (RL) in enhancing the reasoning of large language models (LLMs) is becoming increasingly significant. Despite the success of RL in many scenarios…
Mars-PO: Multi-Agent Reasoning System Preference Optimization
Xiaoxuan Lou, Chaojie Wang, Bo An
Mathematical reasoning is a fundamental capability for large language models (LLMs), yet achieving high performance in this domain remains a significant challenge. The auto-regress…
Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
Chris Yuhao Liu, Liang Zeng, Jiacai Liu +6
In this report, we introduce a collection of methods to enhance reward modeling for LLMs, focusing specifically on data-centric techniques. We propose effective data selection and…