Our code is based on open-r1, with our customized Trainer for mixed SFT+GRPO training. Some other updates focus on the white-box RL (reward function design) and post-completion training (replacement ...
Abstract: This paper studies how AI-assisted programming and large language models (LLM) improve software developers' ability via AI tools (LLM agents) like Github Copilot and Amazon CodeWhisperer, ...
Abstract: Computer scientists often publish their source code accompanying their publications, prominently using code repositories across various domains. Despite the concurrent existence of scholarly ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback