Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to achieve remarkable reasoning in domains like mathematics and coding, where verifiable rewards provide clear signals. However, extending this paradigm to financial decision is challenged by the market's stochastic nature: rewards are verifiable but inherently noisy, causing standard RL to degenerate into reward hacking. To address this, we propose Trade-R1, a model training framework that bridges verifiable rewards to stochastic environments via process-level reasoning verification. Our key innovation is a verification method that transforms the problem of evaluating reasoning over lengthy financial documents into a structured Retrieval-Augmented Generation (RAG) task. We construct a triangular consistency metric, assessing pairwise alignment between retrieved evidence, reasoning chains, and decisions to serve as a validity filter for noisy market returns. We explore two reward integration strategies: Fixed-effect Semantic Reward (FSR) for stable alignment signals, and Dynamic-effect Semantic Reward (DSR) for coupled magnitude optimization. Experiments on different country asset selection demonstrate that our paradigm reduces reward hacking, with DSR achieving superior cross-market generalization while maintaining the highest reasoning consistency.

翻译：强化学习（RL）已使大型语言模型（LLM）在数学和编程等领域实现了卓越的推理能力，这些领域中的可验证奖励提供了清晰的信号。然而，将这一范式扩展到金融决策领域时，市场的随机性带来了挑战：奖励是可验证的，但本质上具有噪声，导致标准RL退化为奖励黑客行为。为解决这一问题，我们提出了Trade-R1，一种通过过程级推理验证将可验证奖励与随机环境相连接的模型训练框架。我们的核心创新是一种验证方法，它将评估长篇金融文档推理的问题转化为结构化的检索增强生成（RAG）任务。我们构建了一个三角一致性度量，评估检索到的证据、推理链和决策之间的两两对齐性，以此作为噪声市场回报的有效性过滤器。我们探索了两种奖励整合策略：用于稳定对齐信号的固定效应语义奖励（FSR），以及用于耦合幅度优化的动态效应语义奖励（DSR）。在不同国家资产选择上的实验表明，我们的范式减少了奖励黑客行为，其中DSR在保持最高推理一致性的同时，实现了更优的跨市场泛化能力。