While LLMs demonstrate strong reasoning capabilities when provided with full information in a single turn, they exhibit substantial vulnerability in multi-turn interactions. Specifically, when information is revealed incrementally or requires updates, models frequently fail to integrate new constraints, leading to a collapse in performance compared to their single-turn baselines. We term the root cause as \emph{Contextual Inertia}: a phenomenon where models rigidly adhere to previous reasoning traces. Even when users explicitly provide corrections or new data in later turns, the model ignores them, preferring to maintain consistency with its previous (incorrect) reasoning path. To address this, we introduce \textbf{R}einforcement \textbf{L}earning with \textbf{S}ingle-\textbf{T}urn \textbf{A}nchors (\textbf{RLSTA}), a generalizable training approach designed to stabilize multi-turn interaction across diverse scenarios and domains. RLSTA leverages the model's superior single-turn capabilities as stable internal anchors to provide reward signals. By aligning multi-turn responses with these anchors, RLSTA empowers models to break contextual inertia and self-calibrate their reasoning based on the latest information. Experiments show that RLSTA significantly outperforms standard fine-tuning and abstention-based methods. Notably, our method exhibits strong cross-domain generalization (e.g., math to code) and proves effective even without external verifiers, highlighting its potential for general-domain applications. Code is available at https://github.com/Tencent/RLSTA.

翻译：尽管大语言模型在单轮交互中拥有完整信息时展现出强大的推理能力，但在多轮交互中却表现出显著脆弱性。具体而言，当信息逐步揭示或需要更新时，模型常无法整合新约束条件，导致性能相比单轮基线产生崩塌。我们将这一根本成因称为"上下文惯性"：即模型僵硬地固守先前推理轨迹的现象。即使用户在后继轮次中明确提供修正或新数据，模型仍忽视这些信息，更倾向于维持与先前（错误）推理路径的一致性。为解决此问题，我们提出**单轮锚点强化学习**（RLSTA），这是一种通用训练方法，旨在跨场景与领域稳定多轮交互。RLSTA利用模型卓越的单轮能力作为稳定内部锚点提供奖励信号，通过将多轮响应与这些锚点对齐，使模型能够打破上下文惯性，依据最新信息自我校准推理过程。实验表明，RLSTA显著优于标准微调和基于弃权的基线方法。值得注意的是，该方法展现出强大的跨领域泛化能力（如从数学到代码），且无需外部验证器即可证明其有效性，凸显了在通用领域应用中的潜力。代码开源地址：https://github.com/Tencent/RLSTA。