做对话系统或客服机器人的团队，SRT解决了长对话中信息稀疏和一致性差的痛点，无需外部模块就能提升效果，值得在长上下文场景中试试。
多轮对话系统在处理长距离依赖时容易丢失关键信息，导致回答不一致。现有方法要么依赖高延迟的外部记忆，要么通过迭代摘要丢失细节。本文提出Self-Recall Thinking (SRT)框架，让模型在推理时自主识别并召回历史有用轮次，生成更一致的回复。SRT包含依赖构建、能力初始化和推理优化三个阶段，通过可验证奖励优化召回和推理。实验表明，SRT在多个数据集上F1提升4.7%，端到端延迟降低14.7%，在推理延迟和准确性间取得更好平衡。
Improving Multi-turn Dialogue Consistency with Self-Recall Thinking
Large language model (LLM) based multi-turn dialogue systems often struggle to track dependencies across non-adjacent turns, undermining both consistency and scalability. As conversations lengthen, essential information becomes sparse and is buried in irrelevant context, while processing the entire dialogue history incurs severe efficiency bottlenecks. Existing solutions either rely on high latency external memory or lose fine-grained details through iterative summarization. In this paper, we propose Self-Recall Thinking (SRT), a framework designed to address long-range contextual dependency and sparse informative signals in multi-turn dialogue. SRT identifies helpful historical turns and uses them to generate contextually appropriate responses, enabling the model to selectively recall and reason over context during inference. This process yields an endogenous reasoning process that integrates interpretable recall steps without external modules. SRT incorporates: (1) Dependency Construction: Generating and converting it into self-recall chains; (2)Capability Initialization: Training to enable reasoning chains with recall tokens capability; (3)Reasoning Improvement: Refining accuracy via verifiable rewards to optimize recall and reasoning for correct answers. Experiments on multiple datasets demonstrate that SRT improves F1 score by 4.7% and reduces end-to-end latency by 14.7% over prior methods, achieving a balance between reasoning latency and accuracy, and outperforming state-of-the-art baselines.