Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination 事件

Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination arXiv:2605.31058v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as the cornerstone for shaping the remarkable coding abilities of Large Language Models (LLMs). However, the scalability of RLVR is severely constrained by the scarcity of sufficiently challenging verifiable code tasks that target near the model's edge of competence. Prior studies often re