Mental health disorders affect hundreds of millions globally, and the Web now serves as a primary medium for accessing support, information, and assessment. Large language models (LLMs) offer scalable and accessible assistance, yet their deployment in mental-health settings remains risky when their reasoning is incomplete, inconsistent, or ungrounded. Existing psychological LLMs emphasize emotional understanding or knowledge recall but overlook the step-wise, clinically aligned reasoning required for appraisal, diagnosis, intervention planning, abstraction, and verification. To address these issues, we introduce MentraSuite, a unified framework for advancing reliable mental-health reasoning. We propose MentraBench, a comprehensive benchmark spanning five core reasoning aspects, six tasks, and 13 datasets, evaluating both task performance and reasoning quality across five dimensions: conciseness, coherence, hallucination avoidance, task understanding, and internal consistency. We further present Mindora, a post-trained model optimized through a hybrid SFT-RL framework with an inconsistency-detection reward to enforce faithful and coherent reasoning. To support training, we construct high-quality trajectories using a novel reasoning trajectory generation strategy, that strategically filters difficult samples and applies a structured, consistency-oriented rewriting process to produce concise, readable, and well-balanced trajectories. Across 20 evaluated LLMs, Mindora achieves the highest average performance on MentraBench and shows remarkable performances in reasoning reliability, demonstrating its effectiveness for complex mental-health scenarios.

翻译：心理健康障碍影响着全球数亿人口，而网络已成为获取支持、信息和评估的主要媒介。大语言模型（LLMs）提供了可扩展且易于获取的辅助手段，然而当它们的推理不完整、不一致或缺乏依据时，在心理健康场景中的部署仍存在风险。现有的心理学大语言模型侧重于情感理解或知识回忆，却忽视了评估、诊断、干预规划、抽象归纳及验证所需的、与临床实践对齐的逐步推理过程。为解决这些问题，我们提出了MentraSuite，一个用于提升可靠心理健康推理的统一框架。我们构建了MentraBench，一个涵盖五个核心推理维度、六项任务及13个数据集的综合性基准，从简洁性、连贯性、幻觉规避、任务理解和内部一致性五个维度评估任务性能与推理质量。我们进一步推出了Mindora，这是一个通过混合SFT-RL框架进行优化的后训练模型，采用不一致性检测奖励机制以确保忠实且连贯的推理。为支持训练，我们通过一种新颖的推理轨迹生成策略构建了高质量轨迹，该策略策略性地筛选困难样本，并应用结构化、以一致性为导向的改写过程，以生成简洁、可读且平衡性良好的轨迹。在评估的20个大语言模型中，Mindora在MentraBench上取得了最高的平均性能，并在推理可靠性方面表现出色，证明了其在复杂心理健康场景中的有效性。