Large Language Models (LLMs) struggle with information forgetting and inefficiency in long-horizon, multi-turn dialogues. To address this, we propose a training-free prompt engineering method, the State-Update Multi-turn Dialogue Strategy. It utilizes "State Reconstruction" and "History Remind" mechanisms to effectively manage dialogue history. Our strategy shows strong performance across multiple multi-hop QA datasets. For instance, on the HotpotQA dataset, it improves the core information filtering score by 32.6%, leading to a 14.1% increase in the downstream QA score, while also reducing inference time by 73.1% and token consumption by 59.4%. Ablation studies confirm the pivotal roles of both components. Our work offers an effective solution for optimizing LLMs in long-range interactions, providing new insights for developing more robust Agents.

翻译：大型语言模型（LLMs）在长时间、多轮对话中面临信息遗忘和效率低下的问题。为此，我们提出一种无需训练的提示工程方法——状态更新多轮对话策略。该方法利用“状态重建”和“历史提醒”机制有效管理对话历史。我们的策略在多个多跳问答数据集上展现出强劲性能。例如，在HotpotQA数据集上，核心信息筛选分数提升了32.6%，下游问答分数相应提高14.1%，同时推理时间减少73.1%，词元消耗降低59.4%。消融实验证实了两个组件的关键作用。本研究为优化LLM在长程交互中的表现提供了有效方案，并为开发更稳健的智能体提供了新见解。