Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs (2024 · 112 citations)
Reward models turn human preferences into a training signal for LLM alignment. Their quality depends heavily on the preference data, and open-source preference datasets tend to be noisy or inconsistently labelled. The authors take a data-first approach. Using only public sources (HelpSteer2, OffsetBias, WildGuardMix…
Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy (2025 · 48 citations)
Open reward models used in RLHF are fragile. High RewardBench scores often fail to carry over to other evaluations, and tweaks to losses or architectures have brought little real progress. The authors argue that the bottleneck is the preference data itself, which is often narrow, synthetically labeled or poorly…
Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs (2025 · 3 citations)
Training LLM agents to fix real GitHub issues is held back by scarce data. Every task needs an executable environment and validated unit tests, and building these by hand is slow, so most public SWE datasets have only a few thousand instances. The authors created an automated, incremental pipeline with three stages…

Co-authors here

12 of 13 co-authors with a page, the most papers together first.

Cited by

Papers of our library cite their works 161 times (of the 149,439 papers whose bibliographies we read); 46 citing papers with a page here →.

Updated 31 October 2026