做 LLM 推理强化学习的团队终于有了可扩展的环境构建方案——RACES 用递归组合替代手动堆叠，效率提升 6 倍，值得关注其开源实现。
RACES 提出一种递归自动组合框架，将可验证环境视为可组合的积木块，通过定义 SEQUENTIAL、PARALLEL、SORT、SELECT 等组合算子，自动融合环境以生成多样化的推理模式。实验表明，基于组合环境的强化学习训练能持续提升推理泛化能力：在 6 个未见基准上，DeepSeek-R1-Distill-Qwen-14B 平均提升 3.1 分，Qwen3-14B 从 58.8 提升至 61.1。仅用 50 个基础环境即可达到 300 个独立环境的训练效果，显著提高环境利用效率。该方法解决了手动构建环境线性扩展的瓶颈，为 LLM 推理能力扩展提供了可扩展的新路径。
Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization
Reinforcement Learning (RL) with verifiable environments has emerged as a powerful approach for enhancing the reasoning capabilities of Large Language Models (LLMs). While prior research demonstrates that scaling environment quantity improves RL performance, existing manual or individual construction methods suffer from linear scaling limits, thereby hindering scalable reasoning generalization. This paper introduces RACES (\textbf{R}ecursive \textbf{A}utomated \textbf{C}omposition for \textbf{E}nvironment \textbf{S}caling), a framework that conceptualizes verifiable environments as composable building blocks that can be recursively assembled. The key insight is that when the codomain (output type) of one environment matches the domain (input type) of another, they can be automatically fused into a new verifiable environment, enabling recursive composition. RACES is implemented with 300 individual environments and defines a set of composition operators (\textsc{SEQUENTIAL}, \textsc{PARALLEL}, \textsc{SORT}, and \textsc{SELECT}) that induce diverse reasoning patterns. Extensive experiments show that RL training on these composite environments consistently enhances reasoning generalization. Specifically, RACES improves DeepSeek-R1-Distill-Qwen-14B by an average of 3.1 points (from 48.2 to 51.3) and boosts Qwen3-14B performance from 58.8 to 61.1 on six benchmarks, which are unseen during the construction of training environments. Moreover, RACES achieves performance comparable to training on 300 individual environments using only 50 base environments, demonstrating significant efficiency in environment utilization.