From the 1 of 2 linked papers with an AI index.
2 papers
cs.AI2026
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
DeepReinforce Team, Ornith Team, Xiaoya Li +4
The paper presents GrandCode, a multi‑agent reinforcement learning system that integrates hypothesis generation, solving, test creation, and summarization modules, and uses a new A…
cs.LG2026
CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning
Songqiao Su, Xiaoya Li, Albert Wang +3
In this paper, we propose CUDA-L2, a system that combines large language models (LLMs) and reinforcement learning (RL) to automatically optimize Half-precision General Matrix Multi…