{"ID":2867712,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.17766","arxiv_id":"2509.17766","title":"A State-Update Prompting Strategy for Efficient and Robust Multi-turn Dialogue","abstract":"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.","short_abstract":"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 effectivel...","url_abs":"https://arxiv.org/abs/2509.17766","url_pdf":"https://arxiv.org/pdf/2509.17766v2","authors":"[\"Ziyi Liu\"]","published":"2025-09-22T13:26:24Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}